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. 4900
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic conditions and cancer

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

    Follows a question

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and code

    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
     الرياضيه
    -0.82
    tagHelperRunner
    -0.75
    Sklici
    -0.74
    Filmografie
    -0.70
     surla
    -0.70
    SneakyThrows
    -0.69
     makeStyles
    -0.67
    LinkId
    -0.67
    RetentionPolicy
    -0.67
    stdafx
    -0.66
    POSITIVE LOGITS
    ________________
    0.93
    <eos>
    0.58
    Leírás
    0.49
    </b>
    0.49
    Attached
    0.47
    posted
    0.46
     
    0.46
    <h2>
    0.45
    낌
    0.43
    InjectAttribute
    0.42
    Activations Density 0.347%

    No Known Activations