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. 2629
    Prev
    Next
    INDEX
    Explanations

    content related to user engagement and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a number indicating helpfulness

    np_acts-logits-general · gemini-2.0-flash

    helpful/not helpful comments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    RectangleBorder
    -0.77
    berdayakan
    -0.71
     doInBackground
    -0.69
    \{\\
    -0.69
    Spoljašnje
    -0.69
     InputDecoration
    -0.69
    ::::::::::::::::
    -0.68
    日閲覧
    -0.67
    setVerticalGroup
    -0.67
    UserScript
    -0.66
    POSITIVE LOGITS
     reply
    0.55
     replies
    0.52
    flag
    0.50
     replied
    0.48
    Flag
    0.48
     Modify
    0.47
     vote
    0.47
     publique
    0.46
    ·
    0.45
    votes
    0.45
    Activations Density 0.295%

    No Known Activations