Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1872
    Prev
    Next
    INDEX
    Explanations

    terms related to viral infections and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     var
    -0.59
     v
    -0.57
     op
    -0.53
     opp
    -0.46
     b
    -0.46
     trans
    -0.46
     ver
    -0.45
     case
    -0.44
     ed
    -0.44
    ENTES
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    1.03
    HasAnnotation
    0.86
    parsedMessage
    0.85
    WithIOException
    0.80
     nahilalakip
    0.80
    ThroughAttribute
    0.79
    Tikang
    0.78
     itſelf
    0.78
    WebElementEntity
    0.78
    complexContent
    0.77
    Activations Density 2.025%

    No Known Activations