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. 62178
    Prev
    Next
    INDEX
    Explanations

    functions related to data serialization and encoding

    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
     EconPapers
    -0.65
    Tembelea
    -0.60
    +#+#
    -0.60
    Hentet
    -0.57
    endphp
    -0.56
     المعيارى
    -0.55
    ptonshire
    -0.54
    
    -0.53
    duled
    -0.51
     ujednoznacz
    -0.49
    POSITIVE LOGITS
    toJSONString
    0.69
    stringify
    0.56
    encode
    0.54
    dumps
    0.54
     jsonify
    0.39
    fromCharCode
    0.39
    setViewportView
    0.38
     Penge
    0.38
     encode
    0.35
    GetBytes
    0.34
    Activations Density 0.008%

    No Known Activations