© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15108
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or making choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.76
    Personensuche
    -0.72
     initComponents
    -0.66
    endregion
    -0.63
    spreis
    -0.59
     Fong
    -0.57
    PerformLayout
    -0.56
    olulu
    -0.55
     PeEnEo
    -0.54
     endregion
    -0.54
    POSITIVE LOGITS
     take
    2.02
    take
    1.95
    Take
    1.94
     Take
    1.91
     TAKE
    1.80
    TAKE
    1.71
    Taking
    1.66
     takes
    1.66
     Taking
    1.65
    taking
    1.63
    Activations Density 0.113%

    No Known Activations