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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14274
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to database management and automation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preferencia
    -0.34
    ритори
    -0.32
    にご
    -0.30
     standard
    -0.28
    参考资料
    -0.28
     padrões
    -0.27
     zit
    -0.26
    QUIZ
    -0.25
    ectl
    -0.24
    憋
    -0.24
    POSITIVE LOGITS
     propOrder
    0.82
     ویکی‌پدی
    0.69
    RenderAtEndOf
    0.64
    TypedDataSet
    0.60
     Houſe
    0.60
    IndentedString
    0.60
     BorderSide
    0.59
     jadx
    0.59
     好文分享
    0.57
     étoit
    0.57
    Activations Density 0.380%

    No Known Activations