Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 12399
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings or criminal justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.79
     poichè
    -0.78
     ainfi
    -0.73
    utilisons
    -0.70
     således
    -0.68
     său
    -0.68
     sahiptir
    -0.67
     auroit
    -0.67
    MMV
    -0.65
     feroit
    -0.65
    POSITIVE LOGITS
     [
    1.03
     really
    0.98
     kind
    0.87
     sort
    0.84
     stuff
    0.82
     maybe
    0.80
     thing
    0.79
     everybody
    0.78
     basically
    0.77
     yeah
    0.76
    Activations Density 1.057%

    No Known Activations