© 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. 6865
    Prev
    Next
    INDEX
    Explanations

    specific references to products, studies, names, expressions, roles, and contractual terms

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

    describing possessive attributes

    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
    bibfield
    -0.40
    essoal
    -0.38
    Referințe
    -0.38
    isSuccess
    -0.38
    utuhkan
    -0.36
    reador
    -0.36
     überhaupt
    -0.36
    arangay
    -0.35
    mnop
    -0.35
    self
    -0.34
    POSITIVE LOGITS
    TagMode
    0.85
    rungsseite
    0.68
    whose
    0.68
    IntoConstraints
    0.67
    ViewImports
    0.62
     незавершена
    0.62
     whofe
    0.61
    InjectAttribute
    0.60
     whose
    0.60
     postIndex
    0.59
    Activations Density 0.031%

    No Known Activations