© 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. 5882
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the inherent nature or characteristics of things

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

    their nature

    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
    WireFormatLite
    -0.46
    IsValid
    -0.36
    FieldBuilder
    -0.35
    bürger
    -0.35
    EnumValue
    -0.34
     getUsername
    -0.34
    getUserName
    -0.33
    isValid
    -0.33
    SerializedSize
    -0.33
    useful
    -0.33
    POSITIVE LOGITS
     nature
    2.50
    nature
    2.13
     natureza
    1.99
     naturaleza
    1.93
     NATURE
    1.87
     Nature
    1.79
    Nature
    1.79
    NATURE
    1.63
     natures
    1.52
     naturen
    1.52
    Activations Density 0.226%

    No Known Activations