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. 20-GEMMASCOPE-RES-131K
    6. 93466
    Prev
    Next
    INDEX
    Explanations

    examples and illustrations of concepts or data

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

    introduces an example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boil
    -0.33
     Immobilien
    -0.33
    今回は
    -0.31
     vervol
    -0.31
     eigenlijk
    -0.31
     Boiling
    -0.30
     ecles
    -0.30
     przede
    -0.30
     Penga
    -0.30
     boil
    -0.29
    POSITIVE LOGITS
     Example
    1.05
     examples
    1.05
     example
    1.03
    Example
    1.02
     Examples
    0.95
    EXAMPLE
    0.95
    Examples
    0.94
    example
    0.94
     EXAMPLE
    0.94
     Beispiele
    0.91
    Activations Density 0.059%

    No Known Activations