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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117315
    Prev
    Next
    INDEX
    Explanations

    keywords related to data structures and classes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    tonode
    -0.54
    errHandler
    -0.52
     typelib
    -0.46
    Демографія
    -0.46
    ⟬
    -0.45
    rizona
    -0.44
    ecycle
    -0.43
    rials
    -0.42
     vertrouwen
    -0.41
    esez
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.58
    الحياه
    0.52
    ReusableCell
    0.47
    PreAuthorize
    0.44
     insuffisamment
    0.43
    PerformLayout
    0.43
    JNIEnv
    0.42
    ControllerAdvice
    0.41
     estekak
    0.40
    *************/
    0.39
    Activations Density 0.127%

    No Known Activations