© 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. 17-GEMMASCOPE-RES-16K
    11. 12961
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements and legal disclaimers in press releases or presentations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zust
    -0.53
     mornings
    -0.52
     Monfieur
    -0.51
    újo
    -0.50
    Charge
    -0.50
    ographiques
    -0.50
    Formats
    -0.50
    charge
    -0.49
     Majefty
    -0.49
    ########.
    -0.49
    POSITIVE LOGITS
     references
    1.16
    references
    0.92
     odkazy
    0.90
     use
    0.88
     incorporate
    0.88
     allusions
    0.83
     mention
    0.80
     References
    0.80
     uses
    0.80
     للمعارف
    0.80
    Activations Density 0.681%

    No Known Activations