© 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. 93230
    Prev
    Next
    INDEX
    Explanations

    references to parental influence and role modeling in decision-making

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

    examples and setting examples

    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
    SourceChecksum
    -0.35
    [++
    -0.25
    Literatur
    -0.25
    DISCOVER
    -0.25
    tsx
    -0.24
     Din
    -0.24
    騒
    -0.24
    arriver
    -0.24
     naman
    -0.24
    ിക്ക
    -0.23
    POSITIVE LOGITS
     example
    2.53
    example
    2.25
     Example
    2.11
     ejemplo
    2.09
    Example
    2.08
     examples
    2.05
     exemplo
    2.05
     EXAMPLE
    2.03
     voorbeeld
    1.95
     esempio
    1.91
    Activations Density 0.083%

    No Known Activations