© 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. 10-GEMMASCOPE-RES-16K
    6. 6175
    Prev
    Next
    INDEX
    Explanations

    references to specific academic or research-related documents and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.44
     vixion
    -0.41
     acuer
    -0.41
     stål
    -0.40
     middag
    -0.39
    clearTimeout
    -0.39
     bor
    -0.39
     satisfaction
    -0.39
    Suivez
    -0.38
    串
    -0.38
    POSITIVE LOGITS
    
    0.98
    CodeAttribute
    0.85
    LookAnd
    0.85
    انيف
    0.83
    <>());
    0.82
    AddTagHelper
    0.80
    RenderAtEndOf
    0.78
    KommentareTeilen
    0.78
    "):
    
    0.77
    oredCriteria
    0.77
    Activations Density 0.135%

    No Known Activations