© 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. 1-GEMMASCOPE-RES-16K
    11. 7667
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal and political contexts, particularly related to civil rights and criminal justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.54
     itſelf
    -0.51
     Majefty
    -0.51
     Anſ
    -0.47
    ſelves
    -0.46
     Richelieu
    -0.46
    ſelf
    -0.46
    cena
    -0.46
    Nationalité
    -0.45
    EndGlobalSection
    -0.45
    POSITIVE LOGITS
    ud
    1.38
    UD
    1.10
     graves
    0.95
     buried
    0.94
    buried
    0.91
     burial
    0.88
     Grave
    0.85
     Burial
    0.82
     grave
    0.82
     burying
    0.82
    Activations Density 0.236%

    No Known Activations