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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5579
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and functions

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

    back list manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     $_"
    -0.67
     Italijanski
    -0.66
     $_[
    -0.64
    |^{
    -0.62
    wiliwch
    -0.61
     zijne
    -0.60
    <unused79>
    -0.60
    <unused41>
    -0.60
    [@BOS@]
    -0.60
    <unused28>
    -0.60
    POSITIVE LOGITS
     back
    0.44
    back
    0.42
    asList
    0.42
     annonces
    0.40
     trasera
    0.40
     redonda
    0.40
     Rücken
    0.39
     Baumann
    0.38
     bahía
    0.38
    Back
    0.38
    Activations Density 0.001%

    No Known Activations