Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 12544
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.01
     виправивши
    -0.87
     initComponents
    -0.75
     resourceCulture
    -0.70
     विश्वसनीयता
    -0.68
    endphp
    -0.68
    DoubleQuotes
    -0.64
    ArrowToggle
    -0.63
    setVerticalGroup
    -0.62
    stateProvider
    -0.62
    POSITIVE LOGITS
    脚注の使い方
    0.57
    PRWEB
    0.55
    ########.
    0.55
    VersionUID
    0.46
    σθαι
    0.44
    mtu
    0.42
     azzurro
    0.42
     gewe
    0.42
    fileId
    0.41
    ots
    0.41
    Activations Density 0.060%

    No Known Activations