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. 297
    Prev
    Next
    INDEX
    Explanations

    requests for communication or contact information

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

    website-related information and contact details (URLs, emails, phone numbers, online communication methods).

    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
     للاسماء
    -0.49
    лтемелер
    -0.46
     cherchés
    -0.46
    Izvori
    -0.43
    providedIn
    -0.43
    AddHtmlAttribute
    -0.42
    ніципалі
    -0.41
     aasta
    -0.41
    TagMode
    -0.41
    rungsseite
    -0.41
    POSITIVE LOGITS
    󠁢
    0.44
     alternatively
    0.39
    Drink
    0.38
    UnsafeEnabled
    0.38
    dą
    0.38
     Tyl
    0.38
     בכ
    0.37
     drop
    0.37
    altern
    0.37
    fjspx
    0.37
    Activations Density 0.103%

    No Known Activations