© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7915
    Prev
    Next
    INDEX
    Explanations

    references to individuals and groups, particularly in the context of their roles or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    whom
    -1.64
    Whom
    -1.48
     whom
    -1.40
    Whose
    -1.38
     Whom
    -1.32
    whose
    -1.28
    who
    -1.24
     Whose
    -1.23
     whose
    -1.00
    Which
    -0.99
    POSITIVE LOGITS
     who
    0.97
    InSection
    0.57
    tangentMode
    0.49
    verifyException
    0.48
    FunctionFlags
    0.47
    DockStyle
    0.47
    Становништво
    0.46
    makeConstraints
    0.46
     bParam
    0.45
    が
    0.44
    Activations Density 0.188%

    No Known Activations