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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12276
    Prev
    Next
    INDEX
    Explanations

    phrases indicating outcomes or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SIS
    -0.88
     @[
    -0.76
     masts
    -0.72
     courseId
    -0.72
     Stroh
    -0.71
    createCanvas
    -0.71
     _('
    -0.71
     rallado
    -0.71
     polycarbonate
    -0.71
     TPR
    -0.71
    POSITIVE LOGITS
     desem
    0.78
     being
    0.72
     quite
    0.72
     be
    0.71
     become
    0.70
     jadi
    0.69
     lượt
    0.69
    andExpect
    0.68
    спеди
    0.67
     побы
    0.67
    Activations Density 0.091%

    No Known Activations