© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    a wide range of terms related to software, programming, and technical specifications

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

    technical or scientific document structures like frame descriptions, metadata, and data extraction details.

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

    domain-specific technical nouns and labels (component names, sample types, subtype/designation terms) in structured or formal text.

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

    technical or scientific text describing objects, specimens, or data items with specific attributes or properties.

    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
    expandindo
    -0.66
     فريبيس
    -0.59
    Diweddarwch
    -0.54
    Ӕ
    -0.54
    sidemargin
    -0.54
    UrlResolution
    -0.53
    uxxxx
    -0.52
    parsedMessage
    -0.50
    ForValue
    -0.49
    verifyException
    -0.49
    POSITIVE LOGITS
    ]._
    0.39
     tarko
    0.35
    таратура
    0.34
     polega
    0.33
     previous
    0.33
     departing
    0.33
     mencakup
    0.32
    ***********/
    0.32
     géneros
    0.31
     zahr
    0.31
    Activations Density 0.523%

    No Known Activations