© 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. 10726
    Prev
    Next
    INDEX
    Explanations

    evidence related to judicial rulings in legal contexts

    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
     Bron
    -0.97
     Alphonse
    -0.94
     BRON
    -0.84
     Bronson
    -0.84
    Bron
    -0.83
     Dawson
    -0.82
    BRON
    -0.81
     Ellie
    -0.79
     Erben
    -0.76
    bron
    -0.74
    POSITIVE LOGITS
     Hag
    0.92
    Hag
    0.84
     Niki
    0.77
     McDonnell
    0.74
     Laguna
    0.72
     Huff
    0.71
     Maureen
    0.71
     RCS
    0.69
    Agu
    0.68
     Durant
    0.68
    Activations Density 1.710%

    No Known Activations