© 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. 17-GEMMASCOPE-RES-16K
    6. 13094
    Prev
    Next
    INDEX
    Explanations

    assertions and expressions of confidence in discussions

    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
     idéia
    -1.11
     biß
    -0.80
     = 
    -0.79
     Arxivat
    -0.74
     iPod
    -0.73
     Arquivado
    -0.73
     "`
    -0.73
     ^_^
    -0.72
     Einfluß
    -0.72
    bootstrapcdn
    -0.70
    POSITIVE LOGITS
     Covid
    1.29
     covid
    1.17
    Covid
    1.11
    covid
    1.11
     COVID
    1.08
     https
    1.07
     pandemia
    0.93
    COVID
    0.91
    https
    0.86
     pandemic
    0.86
    Activations Density 0.127%

    No Known Activations