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. 102992
    Prev
    Next
    INDEX
    Explanations

    programming-related methods and functions associated with user interface components

    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
    :+:
    -0.60
     zwiſchen
    -0.57
    olm
    -0.57
     StringTokenizer
    -0.56
     SQLAlchemy
    -0.55
     Geiſt
    -0.55
    <pad>
    -0.53
    <unused8>
    -0.52
    onedDateTime
    -0.52
    [@BOS@]
    -0.52
    POSITIVE LOGITS
     للاسماء
    0.66
    RenderAtEndOf
    0.65
    setVerticalGroup
    0.58
     viewDidLoad
    0.52
     doInBackground
    0.50
    StoryboardSegue
    0.50
     onOptions
    0.49
     NSCoder
    0.48
    ViewFeatures
    0.47
     onCreateView
    0.45
    Activations Density 0.009%

    No Known Activations