© 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. 13011
    Prev
    Next
    INDEX
    Explanations

    terms related to medical evaluations and responses

    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
    addPreferredGap
    -0.43
    yní
    -0.42
    styleType
    -0.42
    рти
    -0.40
    pushFollow
    -0.40
    IndentedString
    -0.39
    Winning
    -0.39
    WIN
    -0.39
     Winning
    -0.39
     &___
    -0.38
    POSITIVE LOGITS
     inconclusive
    0.88
     reject
    0.78
     refusal
    0.78
     refus
    0.78
     rejecting
    0.74
     rejection
    0.73
     blank
    0.73
     rejects
    0.73
     rejected
    0.72
    ########.
    0.70
    Activations Density 0.614%

    No Known Activations