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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2677
    Prev
    Next
    INDEX
    Explanations

    patterns of time and urgency in numeric formats, particularly concerning dates and appointments

    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
     online
    -0.75
     offline
    -0.62
     Online
    -0.57
    在线
    -0.57
    Online
    -0.57
     ONLINE
    -0.56
    online
    -0.56
     }}^{\
    -0.56
    ordinaire
    -0.56
    apimachinery
    -0.53
    POSITIVE LOGITS
    ArgsConstructor
    0.59
     متعلقه
    0.59
    VersionUID
    0.56
    TabIndex
    0.56
    DataAnnotations
    0.54
    Население
    0.53
    expandindo
    0.53
    новништво
    0.53
    AnimationsModule
    0.53
    bcryptjs
    0.52
    Activations Density 0.080%

    No Known Activations