© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1095
    Prev
    Next
    INDEX
    Explanations

    references to governmental and judicial power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oklahoma
    -0.77
    Oklahoma
    -0.77
    ෝ
    -0.64
     COLORADO
    -0.62
    ූ
    -0.58
     abstrait
    -0.58
     Colorado
    -0.58
    Seattle
    -0.57
    Colorado
    -0.57
    bootstrapcdn
    -0.57
    POSITIVE LOGITS
     Colombo
    1.25
     Sri
    1.24
     Lanka
    1.09
     Sinh
    1.07
    Sri
    1.06
     Ceylon
    1.05
     Kandy
    1.01
     Galle
    0.97
     Lankan
    0.94
     Jaff
    0.92
    Activations Density 0.091%

    No Known Activations