Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 296
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    購入
    -0.68
    開催
    -0.67
    購入した
    -0.59
    大満足
    -0.59
    作って
    -0.57
    お手
    -0.57
     Chernobyl
    -0.55
    pośred
    -0.55
    お金
    -0.54
     createSprite
    -0.53
    POSITIVE LOGITS
     example
    1.03
     the
    1.02
     instance
    1.01
    erun
    0.93
     purposes
    0.91
    geries
    0.84
     reasons
    0.84
    tifies
    0.82
     a
    0.81
    gives
    0.80
    Activations Density 0.581%

    No Known Activations