© 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. 11378
    Prev
    Next
    INDEX
    Explanations

    terms related to legal compliance and adherence to regulations

    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
    apimachinery
    -0.60
     Michoacán
    -0.59
    endous
    -0.58
     McCar
    -0.58
     GenerationType
    -0.57
    squareup
    -0.54
    Scar
    -0.53
    BeginContext
    -0.53
    Coc
    -0.53
    PMailer
    -0.53
    POSITIVE LOGITS
     compliance
    2.17
     Compliance
    1.97
    compliance
    1.95
    Compliance
    1.92
     comply
    1.74
     complies
    1.62
     complying
    1.62
     compliant
    1.62
     violations
    1.58
     conformité
    1.56
    Activations Density 0.314%

    No Known Activations