© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13936
    Prev
    Next
    INDEX
    Explanations

    references to mechanisms of response and control in various contexts

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

    technical or professional language describing responses to problems or challenges.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words that describe a response or reaction to a stimulus or problem.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bypass
    -0.38
    NewLabel
    -0.36
    orti
    -0.36
    ことが
    -0.35
     le
    -0.34
     PANEL
    -0.34
    REGEX
    -0.34
     Cane
    -0.33
     Luc
    -0.33
    elar
    -0.33
    POSITIVE LOGITS
     poprzez
    1.48
     путем
    1.40
     by
    1.34
     pamamagitan
    1.28
     indem
    1.15
     mediante
    1.09
     шля
    0.95
    することで
    0.88
     through
    0.88
     באמצעות
    0.86
    Activations Density 1.918%

    No Known Activations