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. 1784
    Prev
    Next
    INDEX
    Explanations

    URLs or hyperlinks in the text

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

    URLs (https or http)

    np_acts-logits-general · gemini-2.0-flash

    URLs

    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
    esModule
    -0.74
    IndentedString
    -0.73
    WebVitals
    -0.70
    DockStyle
    -0.70
    withIdentifier
    -0.69
    CompleteListener
    -0.68
    PreferredItem
    -0.67
     mergeFrom
    -0.65
    SaveChangesAsync
    -0.65
    ngdoc
    -0.63
    POSITIVE LOGITS
    www
    0.68
     www
    0.64
     https
    0.64
    ://
    0.59
     habet
    0.59
    https
    0.57
     http
    0.55
    ttps
    0.49
    http
    0.49
     financières
    0.45
    Activations Density 0.039%

    No Known Activations