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. 6837
    Prev
    Next
    INDEX
    Explanations

    structures and definitions related to programming or coding, specifically in the context of data management and statistics

    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
     مرئيه
    -0.72
    MessageTagHelper
    -0.69
     للاسماء
    -0.65
    GEBURTSDATUM
    -0.60
     Administrativna
    -0.59
    featureID
    -0.59
    LookAnd
    -0.57
     Paglinawan
    -0.57
     ModelExpression
    -0.56
    MessageOf
    -0.56
    POSITIVE LOGITS
     examined
    0.47
    examined
    0.41
     Exam
    0.40
     tested
    0.39
     assayed
    0.38
     played
    0.37
     Enter
    0.37
     evaluated
    0.37
     tillgäng
    0.37
    Exam
    0.36
    Activations Density 0.875%

    No Known Activations