© 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. 35-GEMMASCOPE-RES-16K
    11. 6810
    Prev
    Next
    INDEX
    Explanations

    keywords related to removal and elimination processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Missing
    -0.41
    Missing
    -0.40
     ulang
    -0.40
    价比
    -0.36
     different
    -0.36
     new
    -0.36
     terecht
    -0.35
    addPreferredGap
    -0.35
     missing
    -0.35
     thiếu
    -0.34
    POSITIVE LOGITS
     unnecessary
    0.87
     khỏi
    0.77
     unwanted
    0.77
     superfluous
    0.76
     redundant
    0.76
     excess
    0.72
     inneces
    0.71
     extraneous
    0.69
     superflu
    0.69
     лиш
    0.68
    Activations Density 0.759%

    No Known Activations