© 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. 69388
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to physics and mathematics, particularly in quantum mechanics

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

    mathematical and expectation symbols

    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
     "$@"
    -0.49
    errHandler
    -0.49
    outWeight
    -0.48
    Rohy
    -0.47
    twimg
    -0.46
     ThemeData
    -0.45
    AlterField
    -0.44
    Cyfeiriadau
    -0.44
     NUKAT
    -0.44
    encodeWith
    -0.44
    POSITIVE LOGITS
    <[
    0.48
    ⟨
    0.46
     expectation
    0.45
    $<
    0.42
     expect
    0.41
    httphttps
    0.41
     inner
    0.41
    (<
    0.39
    =<
    0.39
     《
    0.38
    Activations Density 0.541%

    No Known Activations