© 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. 20-GEMMASCOPE-RES-131K
    6. 70713
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structure

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

    assign `is` `group` `function`

    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
    TagMode
    -0.92
    EDEFAULT
    -0.87
    +#+#
    -0.85
     kasarigan
    -0.82
    IUrlHelper
    -0.81
     Италијани
    -0.78
    RegressionTest
    -0.77
     GenerationType
    -0.73
    ItemBackground
    -0.72
    UserScript
    -0.72
    POSITIVE LOGITS
    Please
    0.33
    <h2>
    0.30
    ↵
    0.30
    isieren
    0.29
    one
    0.29
     habari
    0.29
    <h1>
    0.29
    0.29
     Erscheinung
    0.28
     apsau
    0.28
    Activations Density 0.010%

    No Known Activations