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. 53895
    Prev
    Next
    INDEX
    Explanations

    references to expertise and professional roles in healthcare contexts

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

    Terms indicating professional qualifications, roles, or activities, particularly in academic, research, or technical contexts.

    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
     atlik
    -0.45
     komór
    -0.44
     darbu
    -0.42
     prieš
    -0.42
     vė
    -0.41
     zawod
    -0.41
     الحره
    -0.41
     يتيمه
    -0.40
     Kenntnis
    -0.40
     kabát
    -0.40
    POSITIVE LOGITS
     CURIAM
    0.54
    UnknownFieldSet
    0.48
    AntiForgeryToken
    0.48
    webElement
    0.47
    SequentialGroup
    0.46
    awaiter
    0.46
    InputTagHelper
    0.46
    
    0.43
    writeFieldEnd
    0.43
    jspx
    0.42
    Activations Density 0.128%

    No Known Activations