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. 20-GEMMASCOPE-RES-16K
    6. 16077
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.62
    gameserver
    -0.53
    scriptcase
    -0.53
    httphttps
    -0.51
     Vard
    -0.50
    клопе
    -0.49
     comod
    -0.49
     来自
    -0.48
    Население
    -0.47
    mphony
    -0.47
    POSITIVE LOGITS
     noDo
    0.68
     allAfrica
    0.63
     verla
    0.59
    nly
    0.57
    TintMode
    0.56
    pening
    0.55
     LoginComponent
    0.54
    strich
    0.54
    ℗
    0.53
    audiovisuel
    0.53
    Activations Density 0.423%

    No Known Activations