© 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. 9-GEMMASCOPE-RES-131K
    11. 5375
    Prev
    Next
    INDEX
    Explanations

    references to structured data or content types within code or document formats

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

    references and citations

    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
    الحياه
    -0.52
    Portail
    -0.50
    RegressionTest
    -0.44
    featureID
    -0.43
    rrggbb
    -0.40
    MethodManager
    -0.40
    Pozri
    -0.39
    BagLayout
    -0.39
    醐
    -0.38
     initComponents
    -0.38
    POSITIVE LOGITS
     reference
    1.69
     Reference
    1.52
     references
    1.52
    reference
    1.43
     References
    1.36
    Reference
    1.35
     REFERENCE
    1.33
     referencia
    1.29
     riferimento
    1.28
    references
    1.26
    Activations Density 0.338%

    No Known Activations