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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12115
    Prev
    Next
    INDEX
    Explanations

    systematic or code-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pédie
    -0.38
     LIVE
    -0.34
     COLON
    -0.31
    ParameterName
    -0.30
    资讯
    -0.30
     message
    -0.30
    live
    -0.30
    getWriter
    -0.30
     mensaje
    -0.29
    씩
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.73
    isContained
    0.71
    WebVitals
    0.69
    Personendaten
    0.65
    twimg
    0.62
    elemField
    0.59
     kaarangay
    0.58
    MigrationBuilder
    0.57
    :✨
    0.56
    ronpa
    0.56
    Activations Density 0.089%

    No Known Activations