Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 65366
    Prev
    Next
    INDEX
    Explanations

    statements related to hypotheses in scientific research

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

    testing null hypothesis

    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
    таратура
    -0.53
    MigrationBuilder
    -0.52
     StringTokenizer
    -0.52
    makeText
    -0.51
    .*")]
    -0.47
    liferay
    -0.47
    detectChanges
    -0.46
    kloped
    -0.44
     actionPerformed
    -0.43
     surla
    -0.41
    POSITIVE LOGITS
     hypothesis
    1.74
     hypotheses
    1.58
     Hypothesis
    1.48
    Hypothesis
    1.41
     hipótesis
    1.40
    hypothesis
    1.38
     Hypotheses
    1.28
     hypothe
    1.17
     hypothesized
    1.17
     null
    0.90
    Activations Density 0.345%

    No Known Activations