© 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. 14880
    Prev
    Next
    INDEX
    Explanations

    positivity and growth in various contexts, particularly related to outcomes and personal input

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tinyos
    -0.49
    الدراسه
    -0.48
    ImageContext
    -0.48
    Rhestr
    -0.46
    Tembelea
    -0.44
    OPSIS
    -0.42
     Argos
    -0.41
     onStop
    -0.41
    ⌉
    -0.40
    figsize
    -0.40
    POSITIVE LOGITS
    WithIOException
    0.48
     conoscenza
    0.42
    ském
    0.40
    EDEFAULT
    0.40
    ského
    0.39
    transQ
    0.38
     comodidad
    0.37
     ones
    0.37
    adaptiveStyles
    0.37
     sekitarnya
    0.36
    Activations Density 0.636%

    No Known Activations