© 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. 40550
    Prev
    Next
    INDEX
    Explanations

    boolean states and specific conditions related to scientific classifications

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

    false); anaerobic straight; even and

    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
    RegressionTest
    -1.19
    ChildScrollView
    -1.12
    :✨
    -1.02
    +#+#
    -1.02
    <unused28>
    -0.98
    <unused16>
    -0.98
    <unused14>
    -0.98
    <unused23>
    -0.98
    <unused3>
    -0.98
    [@BOS@]
    -0.98
    POSITIVE LOGITS
    UseVisualStyle
    1.03
    ↵↵
    0.32
    .
    0.31
     surface
    0.27
    ↵
    0.23
    0
    0.22
     blue
    0.22
    P
    0.22
    BackgroundColor
    0.22
     yellow
    0.21
    Activations Density 0.000%

    No Known Activations