© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 46439
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion or personal sentiments

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

    I don't know

    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
    MigrationBuilder
    -0.62
     yearly
    -0.51
    definitely
    -0.49
     downfall
    -0.49
     definitely
    -0.48
     mentality
    -0.47
     ""],
    -0.47
     hindering
    -0.46
    '">
    -0.45
     pertaining
    -0.45
    POSITIVE LOGITS
     extraordinarily
    0.62
    Frankly
    0.54
     manifestly
    0.53
     enormously
    0.50
     arrayed
    0.49
    ⁦
    0.49
    arXiv
    0.49
     evidentemente
    0.49
    chartInstance
    0.49
     daarvan
    0.49
    Activations Density 0.145%

    No Known Activations