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. 1782
    Prev
    Next
    INDEX
    Explanations

    structured sections of scientific papers, particularly those detailing methods, results, and discussions

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

    Text preceding section numbers

    np_acts-logits-general · gemini-2.0-flash

    section headings and numbers

    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
    <bos>
    -0.47
     También
    -0.44
    if
    -0.43
    ул
    -0.43
    Nope
    -0.43
     somewhere
    -0.43
     нем
    -0.42
    جغرافيا
    -0.42
     jist
    -0.41
    magine
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.88
    ंदीखरीदारी
    0.84
     utafitiHapana
    0.83
     estimés
    0.81
    RectangleBorder
    0.75
     }}"></
    0.72
     Chwiliwch
    0.71
    \{\\
    0.70
     doInBackground
    0.70
     BoxFit
    0.69
    Activations Density 0.223%

    No Known Activations