© 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. 23-GEMMASCOPE-RES-16K
    6. 12198
    Prev
    Next
    INDEX
    Explanations

    references to personal injury law and legal advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.79
    tagHelperRunner
    -0.71
    (!__
    -0.62
     aDecoder
    -0.60
    makeConstraints
    -0.57
    脚注の使い方
    -0.56
    migrationBuilder
    -0.55
    GOTREF
    -0.55
    Favourite
    -0.55
     BnF
    -0.54
    POSITIVE LOGITS
     attorney
    0.72
     attorneys
    0.68
     defense
    0.67
     wrongful
    0.67
     aggressively
    0.67
     injury
    0.67
     Injury
    0.64
     aggressive
    0.63
    Attorney
    0.63
     defending
    0.63
    Activations Density 0.254%

    No Known Activations