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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1085
    Prev
    Next
    INDEX
    Explanations

    HTML structural elements and tags related to navigation and layout

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

    HTML elements used for structuring navigation menus

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

    HTML tags and technical terms

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     createState
    -0.72
    LookAnd
    -0.72
     تانيه
    -0.71
    WithIOException
    -0.69
     '{@
    -0.68
    Diwedd
    -0.68
     StringTokenizer
    -0.67
     дописавши
    -0.67
     tartalomajánló
    -0.66
    ">:
    -0.64
    POSITIVE LOGITS
    ><!--
    0.57
    RTRS
    0.47
    Problem
    0.46
    sendRedirect
    0.45
    <!
    0.44
    ProgressHUD
    0.43
    <eos>
    0.43
    EntityFramework
    0.42
     else
    0.42
     nhiêu
    0.41
    Activations Density 0.024%

    No Known Activations