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. 73452
    Prev
    Next
    INDEX
    Explanations

    specific references to medical language and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Important tokens that provide technical specificity in academic, scientific, or programming contexts, often appearing in references, property descriptions, medical terminology, or methodological annotations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    XmlEnum
    -0.44
     مرئيه
    -0.42
    
    -0.41
    textAppearance
    -0.39
    enderror
    -0.38
     ESTABL
    -0.37
     stack
    -0.37
     vacacionales
    -0.36
     established
    -0.35
    mybatisplus
    -0.35
    POSITIVE LOGITS
    parsedMessage
    0.53
    makeText
    0.53
    IUrlHelper
    0.49
    ISupport
    0.44
     mergeFrom
    0.44
    
    0.42
     getVersion
    0.42
    版本的
    0.42
    BoxShadow
    0.42
    配套
    0.42
    Activations Density 0.382%

    No Known Activations