© 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 EvalsExportsinterp-engineNEWAPI 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. 4182
    Prev
    Next
    INDEX
    Explanations

    mentions of financial matters and policies

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

    lists of related items or concepts separated by commas or dashes.

    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
     aceea
    -0.50
     infatti
    -0.50
     Infatti
    -0.45
    というか
    -0.41
     acela
    -0.40
    erdings
    -0.40
    unlike
    -0.39
     שוליים
    -0.39
     vroeger
    -0.38
    tamment
    -0.37
    POSITIVE LOGITS
     all
    1.71
     allemaal
    1.48
    这一切
    1.30
     semuanya
    1.24
    すべて
    1.23
     tudo
    1.16
    全て
    1.15
    どれも
    1.14
     semua
    1.12
     tutto
    1.11
    Activations Density 0.860%

    No Known Activations