© 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. 31-GEMMASCOPE-RES-131K
    6. 12719
    Prev
    Next
    INDEX
    Explanations

    references to periods of time, particularly in years or decades

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

    time spans and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UseVisualStyle
    -0.39
    Попис
    -0.37
     ComVisible
    -0.34
     antes
    -0.32
     before
    -0.31
    这时
    -0.29
    regist
    -0.29
    kör
    -0.29
     DURING
    -0.29
     total
    -0.28
    POSITIVE LOGITS
    OGND
    0.84
     nahilalakip
    0.71
    écart
    0.55
    
    0.55
    PyExc
    0.55
    <unused93>
    0.55
     distanza
    0.54
     myö
    0.54
    <pad>
    0.54
    <unused48>
    0.54
    Activations Density 0.018%

    No Known Activations