Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 24555
    Prev
    Next
    INDEX
    Explanations

    beginning of new sections or paragraphs in the text

    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
    SourceChecksum
    -0.59
    WebVitals
    -0.56
     الحره
    -0.48
    featureID
    -0.47
     betweenstory
    -0.47
    CloseOperation
    -0.46
     invokingState
    -0.44
    TagMode
    -0.44
    AppMethodBeat
    -0.43
    fjspx
    -0.43
    POSITIVE LOGITS
    Filmographie
    0.46
     breath
    0.43
     aesthetically
    0.41
     Fati
    0.41
     BufferedImage
    0.41
     initComponents
    0.41
     cliche
    0.39
    ERVIEW
    0.38
     sniff
    0.38
     pain
    0.38
    Activations Density 0.065%

    No Known Activations