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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 124878
    Prev
    Next
    INDEX
    Explanations

    references to specific hormones or genetic markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     незавершена
    -0.73
    GOTREF
    -0.72
    الدراسه
    -0.69
    ibase
    -0.68
    存于互联网档案馆
    -0.65
    seri
    -0.65
    oia
    -0.64
     dAtA
    -0.64
    EndInit
    -0.63
    ➟
    -0.63
    POSITIVE LOGITS
    gh
    0.93
     Gh
    0.69
     gh
    0.66
    GH
    0.64
    Gh
    0.64
     Pugh
    0.63
    igh
    0.60
     Ghe
    0.57
     GH
    0.57
    IGH
    0.56
    Activations Density 0.015%

    No Known Activations