© 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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1857
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.82
     EconPapers
    -0.66
    awtextra
    -0.66
     Codable
    -0.65
     ModelExpression
    -0.64
     مرئيه
    -0.64
    setVerticalGroup
    -0.63
     myſelf
    -0.63
    PerformLayout
    -0.63
     itſelf
    -0.62
    POSITIVE LOGITS
    goTo
    0.59
     the
    0.59
     goTo
    0.53
     goto
    0.51
    moveTo
    0.51
     places
    0.50
     visit
    0.47
     Goto
    0.46
    GoTo
    0.46
    Goto
    0.45
    Activations Density 0.362%

    No Known Activations