© 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. 10653
    Prev
    Next
    INDEX
    Explanations

    incidents involving protests and gatherings

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

    large crowds of people gathering in physical locations.

    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
    ToLeft
    -0.41
    ulipas
    -0.34
     समीक्षाओं
    -0.33
     Kombat
    -0.33
     travel
    -0.33
    净
    -0.32
    其中的
    -0.31
     Vikipedi
    -0.31
     Penh
    -0.31
     plonge
    -0.30
    POSITIVE LOGITS
     outside
    1.69
    Outside
    1.60
    outside
    1.55
     Outside
    1.51
     OUTSIDE
    1.41
    OUTSIDE
    1.30
     afuera
    1.26
     utanför
    1.13
     buiten
    0.98
     dehors
    0.95
    Activations Density 0.228%

    No Known Activations