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. 28128
    Prev
    Next
    INDEX
    Explanations

    terms related to gauge theories and legal contexts, particularly in the realm of habeas corpus

    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
     صوتيه
    -0.76
    httphttps
    -0.73
     Taktlose
    -0.68
    ConstraintMaker
    -0.68
    Демографія
    -0.68
    icitis
    -0.63
    webElementXpaths
    -0.61
     himo
    -0.60
     فريبيس
    -0.60
    ніципалі
    -0.60
    POSITIVE LOGITS
     stuk
    0.40
     shy
    0.36
    ์
    0.35
    InteropServices
    0.34
    த்
    0.33
    lunda
    0.33
    POSIX
    0.32
    ,
    0.32
     rote
    0.32
    wärts
    0.32
    Activations Density 0.165%

    No Known Activations