© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6689
    Prev
    Next
    INDEX
    Explanations

    references to leadership styles and their application in management contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic research methodology and study details (like aims, methods, data collection, participants, etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    language signaling a formal scholarly study, especially references to its aims, methods, participants, data collection, and reporting structure.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    academic or research study methodology sections, particularly phrases describing the research design, participants, and data collection methods.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.71
     للمعارف
    -0.47
     nakalista
    -0.46
     silhouettes
    -0.44
     surreal
    -0.43
     accolades
    -0.42
     traps
    -0.42
     couscous
    -0.42
    +#+#
    -0.41
    uvwxyz
    -0.41
    POSITIVE LOGITS
    isContained
    0.48
    consulté
    0.44
     HasFactory
    0.38
     izvē
    0.37
    Hochspringen
    0.36
     interesado
    0.36
     involucrados
    0.35
    PreInfinity
    0.35
    contentLoaded
    0.35
     interesados
    0.34
    Activations Density 0.120%

    No Known Activations