© 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. 37-GEMMASCOPE-RES-16K
    11. 2413
    Prev
    Next
    INDEX
    Explanations

    references to group identity and membership, particularly in a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.43
     ब्रेकडाउन
    -0.42
    principalColumn
    -0.37
     ostavi
    -0.36
    LookAnd
    -0.36
    Individual
    -0.35
    Chairman
    -0.35
     magasiner
    -0.35
    Areas
    -0.35
    
    -0.35
    POSITIVE LOGITS
     crew
    1.45
     group
    1.44
     gang
    1.35
     cohort
    1.30
     squad
    1.23
     bunch
    1.19
     troupe
    1.17
     tribe
    1.15
     posse
    1.13
     grupo
    1.11
    Activations Density 0.812%

    No Known Activations