© 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. 15-GEMMASCOPE-RES-16K
    11. 8854
    Prev
    Next
    INDEX
    Explanations

    terms related to responsibilities in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     individuel
    -0.52
    yentes
    -0.51
     individuale
    -0.50
    EndContext
    -0.48
    roglo
    -0.47
    Портал
    -0.46
    tagHelperRunner
    -0.46
    unik
    -0.44
    ग्री
    -0.43
    Individual
    -0.43
    POSITIVE LOGITS
     substitute
    0.95
     substituting
    0.88
     replacing
    0.87
     substituted
    0.87
    substitute
    0.86
     substitutes
    0.85
     remplace
    0.83
    substituted
    0.83
     substitution
    0.82
     interim
    0.82
    Activations Density 0.284%

    No Known Activations