© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 73649
    Prev
    Next
    INDEX
    Explanations

    key terms related to medical and scientific protocols or classifications

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

    specific scientific terms

    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
    EndInit
    -0.81
     صوتيه
    -0.77
     invokingState
    -0.69
    OGND
    -0.69
     ModelExpression
    -0.66
    RegressionTest
    -0.66
    :✨
    -0.65
     виправивши
    -0.65
    StoryboardSegue
    -0.65
     noDo
    -0.63
    POSITIVE LOGITS
    lah
    0.36
    Â
    0.35
    Cast
    0.34
    ųjų
    0.32
     â
    0.31
     ANS
    0.30
    了一口
    0.30
     Capital
    0.30
     Qu
    0.30
    yecto
    0.29
    Activations Density 0.104%

    No Known Activations