© 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. 111075
    Prev
    Next
    INDEX
    Explanations

    religious language and references, particularly those related to faith and biblical concepts

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

    prophets and kings

    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
    yarnpkg
    -0.57
     تضيفلها
    -0.54
    addPreferredGap
    -0.51
    URLException
    -0.50
     AssemblyVersion
    -0.49
    buttonText
    -0.49
    日閲覧
    -0.48
    blouse
    -0.47
    CrossRef
    -0.47
    TokenNameEQUAL
    -0.47
    POSITIVE LOGITS
     Ezekiel
    0.43
    Ezek
    0.41
     informes
    0.39
     humain
    0.38
     inspección
    0.38
     Italijani
    0.36
     rueda
    0.35
     humaine
    0.35
     respeto
    0.34
     insight
    0.34
    Activations Density 0.004%

    No Known Activations