Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 368
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to functions and variables

    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
    migrationBuilder
    -0.40
    kfree
    -0.39
    MENAFN
    -0.38
     headlines
    -0.37
    RouterModule
    -0.35
    setupUi
    -0.35
     vou
    -0.35
     helps
    -0.33
     judiciaire
    -0.33
     ית
    -0.33
    POSITIVE LOGITS
     surla
    0.68
    IVEREF
    0.56
    rungsseite
    0.53
     geïsole
    0.52
     ſind
    0.52
     Мексичка
    0.51
    zondere
    0.50
    السكان
    0.49
     persoonlijke
    0.49
     farba
    0.49
    Activations Density 1.712%

    No Known Activations