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. 20-GEMMASCOPE-RES-16K
    6. 64
    Prev
    Next
    INDEX
    Explanations

    specific programming or markup language keywords and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming language syntax and code structure.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    LookAnd
    -0.42
    TypedArray
    -0.41
    وصلات
    -0.39
    XmlAccessType
    -0.39
    URLException
    -0.39
    AlterField
    -0.38
    beforeEach
    -0.38
     onStart
    -0.37
     Rine
    -0.37
    XmlRootElement
    -0.36
    POSITIVE LOGITS
    mybatisplus
    0.85
     فريبيس
    0.62
     Verſ
    0.51
    Ծանոթ
    0.50
    NUMX
    0.48
     ſind
    0.48
    rungsseite
    0.46
     ilustracja
    0.45
    baomidou
    0.45
    zbęd
    0.45
    Activations Density 0.008%

    No Known Activations