© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3983
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual or entity named 'Pal', particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     griech
    -0.38
     caza
    -0.36
     juzgar
    -0.35
    hoga
    -0.33
     griechischen
    -0.32
    Jereo
    -0.32
     grecque
    -0.31
    bitField
    -0.31
     Greek
    -0.31
    Lost
    -0.30
    POSITIVE LOGITS
     Pal
    0.93
    Pal
    0.90
     informée
    0.82
    ScopeManager
    0.77
     pal
    0.77
    pal
    0.75
    addComponent
    0.73
    setVerticalGroup
    0.70
     GenerationType
    0.69
    CrossRef
    0.65
    Activations Density 0.564%

    No Known Activations