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. 651
    Prev
    Next
    INDEX
    Explanations

    references to standards and specifications, specifically those related to materials and manufacturing

    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
    ReusableCell
    -0.38
    SharedCtor
    -0.36
    IsMutable
    -0.35
     везе
    -0.35
    EndInit
    -0.34
     sco
    -0.33
    tyg
    -0.33
     ویکی‌آمباردا
    -0.33
    })+\
    -0.33
     }}{\
    -0.33
    POSITIVE LOGITS
    PMailer
    0.57
     kasarigan
    0.54
    Попис
    0.51
     plufieurs
    0.47
    ########.
    0.45
     towarzys
    0.45
    tonsoft
    0.44
    活
    0.44
    ankind
    0.43
    UserScript
    0.43
    Activations Density 0.012%

    No Known Activations