© 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. 21-GEMMASCOPE-RES-16K
    6. 14069
    Prev
    Next
    INDEX
    Explanations

    numerical evaluations or metrics related to performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.61
    SourceChecksum
    -0.59
     ""))
    -0.57
    isations
    -0.56
     ""],
    -0.55
     متعلقه
    -0.55
    Bibliograf
    -0.55
    )')
    -0.54
    
    -0.53
    uasion
    -0.53
    POSITIVE LOGITS
    card
    0.98
    board
    0.80
     Scores
    0.78
    boards
    0.77
    heet
    0.75
    cards
    0.74
     scores
    0.71
    scores
    0.70
     CURIAM
    0.70
    BOARD
    0.68
    Activations Density 0.059%

    No Known Activations