© 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. 31-GEMMASCOPE-RES-16K
    11. 12199
    Prev
    Next
    INDEX
    Explanations

    actions related to decision-making and transitions

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

    phrasal verbs with "out" as the particle (pull out, pick out, dig out, point out, carry out).

    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
    LookAnd
    -0.42
    toContain
    -0.34
     You
    -0.34
    DispatchToProps
    -0.33
    UrlResolution
    -0.33
    GenerationType
    -0.32
    FormData
    -0.32
    LikeLike
    -0.32
    FromNib
    -0.32
     pr
    -0.31
    POSITIVE LOGITS
     up
    0.90
    +#+#
    0.67
     out
    0.64
    fromnode
    0.61
     down
    0.57
     Wikiseite
    0.54
    saraba
    0.49
     ब्रेकडाउन
    0.48
     off
    0.46
    Билгалдахарш
    0.46
    Activations Density 0.467%

    No Known Activations