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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3623
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual observation and measurement in a scientific context

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

    terms related to visual field of view, particularly in optical and imaging contexts.

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

    mentions of visual field or viewing range/scope.

    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
     Hypothe
    -0.32
    网上
    -0.30
    tgärder
    -0.29
     WALTZ
    -0.28
    UnsafeEnabled
    -0.28
     Ян
    -0.28
     ân
    -0.28
    getLayout
    -0.27
    WebRequest
    -0.27
     Atro
    -0.27
    POSITIVE LOGITS
     vision
    1.66
     view
    1.63
     sight
    1.51
     Sicht
    1.32
    视野
    1.31
    vision
    1.30
     Vision
    1.27
     visão
    1.26
    view
    1.25
     visión
    1.25
    Activations Density 0.336%

    No Known Activations