© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 9909
    Prev
    Next
    INDEX
    Explanations

    military ranks and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.96
    \{\\
    -0.78
     itſelf
    -0.74
     Signalez
    -0.74
     كومونز
    -0.73
     utafitiHapana
    -0.72
    reportWebVitals
    -0.71
    featureID
    -0.70
    WebMethod
    -0.70
     AllAfrica
    -0.69
    POSITIVE LOGITS
     captain
    1.06
     captains
    0.98
     Captain
    0.96
     colonel
    0.95
    Captain
    0.93
     CAPTAIN
    0.92
     capitaine
    0.91
     Colonel
    0.90
    Colonel
    0.89
    captain
    0.89
    Activations Density 0.242%

    No Known Activations