© 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. 34-GEMMASCOPE-RES-16K
    6. 11193
    Prev
    Next
    INDEX
    Explanations

    phrases related to "taking" actions or considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日閲覧
    -0.41
    ymce
    -0.41
    VersionUID
    -0.40
    endregion
    -0.39
     consectetur
    -0.33
    //
    -0.32
    EndTag
    -0.32
     ffilmiau
    -0.32
     InputDecoration
    -0.32
    }$​
    -0.31
    POSITIVE LOGITS
     seriously
    0.88
     advantage
    0.75
    seriously
    0.73
     cue
    0.71
     Seriously
    0.71
     aback
    0.71
     hostage
    0.71
     plunge
    0.69
     cues
    0.67
     precautions
    0.66
    Activations Density 0.162%

    No Known Activations