© 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. 31-GEMMASCOPE-RES-16K
    11. 14373
    Prev
    Next
    INDEX
    Explanations

    technical terms and relationships in scientific or medical contexts

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

    mathematical or technical notation involving variables and symbols.

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

    mathematical and technical notation, particularly variables and symbols in formal expressions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    variable names or identifiers in mathematical or technical notation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.73
    +#+#
    -0.71
     EconPapers
    -0.69
    contentLoaded
    -0.67
     autorytatywna
    -0.65
    addGap
    -0.65
    ➯
    -0.65
     Paglinawan
    -0.61
     GenerationType
    -0.60
    complexContent
    -0.59
    POSITIVE LOGITS
     is
    1.18
     are
    0.82
     là
    0.61
     är
    0.53
    是
    0.52
     adalah
    0.51
    return
    0.51
     êtes
    0.50
     be
    0.49
     was
    0.49
    Activations Density 0.368%

    No Known Activations