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

    Neuronpedia

    APICircuit 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. 5431
    Prev
    Next
    INDEX
    Explanations

    expressions of confidence and self-assurance

    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
     Ber
    -0.62
     West
    -0.61
     Gow
    -0.58
    ar
    -0.56
     ber
    -0.56
     par
    -0.55
    ir
    -0.54
    sel
    -0.54
     Brum
    -0.54
    ber
    -0.53
    POSITIVE LOGITS
     myſelf
    1.44
     itſelf
    1.30
     themſelves
    1.25
    confidence
    1.25
     confidence
    1.25
     Jefus
    1.24
     pleaſure
    1.24
     himſelf
    1.21
     Confidence
    1.20
     ſeveral
    1.20
    Activations Density 0.129%

    No Known Activations