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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 9617
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the nature and characteristics of concepts and ideas

    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
    RenderAtEndOf
    -0.52
    исленность
    -0.46
    ſelf
    -0.44
    fillType
    -0.44
    unconfirmed
    -0.43
     mergeFrom
    -0.43
    windowFixed
    -0.42
     sqlSession
    -0.41
    ThroughAttribute
    -0.41
    الدراسه
    -0.40
    POSITIVE LOGITS
     overrated
    0.60
     everywhere
    0.53
     fickle
    0.52
     bigger
    0.51
     inherently
    0.51
     ALWAYS
    0.49
     never
    0.49
     always
    0.48
     intrinsically
    0.47
     about
    0.47
    Activations Density 0.457%

    No Known Activations