© 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. 9-GEMMASCOPE-RES-131K
    6. 107292
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effects and influences of substances on health outcomes

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

    causation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.77
     betweenstory
    -0.75
    mybatisplus
    -0.71
    MLLoader
    -0.68
    WebServlet
    -0.68
    keyColumn
    -0.67
    ロウィン
    -0.63
     Majefty
    -0.63
    windowFixed
    -0.62
     houſe
    -0.61
    POSITIVE LOGITS
     particularly
    0.29
    <eos>
    0.29
     derive
    0.28
     be
    0.28
     however
    0.28
    derive
    0.28
     Tam
    0.27
     tam
    0.26
     yield
    0.26
     However
    0.26
    Activations Density 0.136%

    No Known Activations