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. 33-GEMMASCOPE-RES-131K
    6. 65879
    Prev
    Next
    INDEX
    Explanations

    programming functions and their definitions

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubov
    -0.43
    gdx
    -0.41
    addComponent
    -0.38
    routeProvider
    -0.38
     Reiss
    -0.36
    antry
    -0.36
     gyhoeddwyd
    -0.35
    [{{
    -0.35
    uples
    -0.35
     Citation
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    0.53
    ↹
    0.49
    SharedDtor
    0.49
     مشين
    0.48
    jsxFileName
    0.47
     betweenstory
    0.47
     noDo
    0.45
    webElementXpaths
    0.44
    SharedCtor
    0.44
     indisponible
    0.43
    Activations Density 0.005%

    No Known Activations