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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 105155
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to reproduction and related processes

    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
    stdc
    -0.63
    DotNetBar
    -0.62
    Stack
    -0.58
    Elder
    -0.57
    Jar
    -0.56
    City
    -0.55
    heta
    -0.55
     CITY
    -0.54
     City
    -0.54
     marketers
    -0.54
    POSITIVE LOGITS
     reproduction
    0.92
     reproduce
    0.84
     reproduced
    0.83
     reproductions
    0.77
     reproducing
    0.72
     reproduces
    0.71
    Reprodu
    0.71
     reprodução
    0.70
     Reproduction
    0.66
    Reproduction
    0.65
    Activations Density 0.007%

    No Known Activations