© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38907
    Prev
    Next
    INDEX
    Explanations

    references to coupon codes and download instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    download and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.71
    CloseOperation
    -0.69
     الحره
    -0.68
    [@BOS@]
    -0.66
    <unused74>
    -0.66
    <unused28>
    -0.66
    <unused51>
    -0.66
    <unused43>
    -0.66
    <unused8>
    -0.66
    <unused16>
    -0.66
    POSITIVE LOGITS
    ᅠ
    0.40
    :✨
    0.36
     Sar
    0.32
     simplifié
    0.32
     Paul
    0.31
      
    0.30
    ActionTypes
    0.30
     V
    0.30
    opsida
    0.30
    co
    0.30
    Activations Density 0.042%

    No Known Activations