© 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. 4859
    Prev
    Next
    INDEX
    Explanations

    references to various types of news broadcasts and their characteristics

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

    lists and enumerations of items organized by category or geographic location.

    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
    GTCX
    -0.50
    PMailer
    -0.46
     >=",
    -0.43
    OCCURRED
    -0.42
    couvrez
    -0.40
     oprot
    -0.40
    gico
    -0.39
    ARROLL
    -0.39
     Obtenez
    -0.39
    exterior
    -0.39
    POSITIVE LOGITS
     local
    3.08
    local
    2.63
     locally
    2.59
     LOCAL
    2.39
     lokal
    2.36
    Local
    2.36
     Local
    2.33
     lokale
    2.28
    LOCAL
    2.13
     lokalen
    2.13
    Activations Density 0.939%

    No Known Activations