© 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. 41140
    Prev
    Next
    INDEX
    Explanations

    references and external links in text

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

    references external links

    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
    MigrationBuilder
    -0.67
     utafitiHapana
    -0.65
     ब्रेकडाउन
    -0.60
     textStatus
    -0.57
    protoimpl
    -0.57
    ----</
    -0.57
    SequentialGroup
    -0.56
    ⟬
    -0.56
    keyColumn
    -0.56
    <unused14>
    -0.54
    POSITIVE LOGITS
    <eos>
    0.33
    :✨
    0.32
    پیوند
    0.32
    RectangleBorder
    0.32
     bestaat
    0.31
     additional
    0.30
    WindowListener
    0.30
     sum
    0.30
     )
    0.29
     guten
    0.29
    Activations Density 0.005%

    No Known Activations