© 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. 27976
    Prev
    Next
    INDEX
    Explanations

    phrases related to data sharing and privacy concerns

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

    technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions requests for access to information or disclosure of data/documents.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    queryInterface
    -0.54
     NavController
    -0.47
     وتسجيلات
    -0.47
     ModelExpression
    -0.47
    ISupport
    -0.47
     censiti
    -0.46
     للمعارف
    -0.45
    BeginInit
    -0.45
    selfish
    -0.42
    mybatisplus
    -0.42
    POSITIVE LOGITS
    )}</
    0.38
     Ganes
    0.35
    useState
    0.34
    indu
    0.33
    ől
    0.33
     rak
    0.33
    cout
    0.32
    CodeAnalysis
    0.32
     useState
    0.32
    ^(@
    0.31
    Activations Density 0.168%

    No Known Activations