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. 6802
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to programming and data structures

    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
     fast
    -0.33
    fe
    -0.31
    fast
    -0.30
     fo
    -0.29
    CDCl
    -0.29
    msgTypes
    -0.29
     careful
    -0.28
    ↵↵
    -0.28
    volen
    -0.27
     Fe
    -0.26
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
     ब्रेकडाउन
    0.77
    LabelTagHelper
    0.75
    .*")]
    0.70
     NSCoder
    0.70
     فريبيس
    0.69
     ſche
    0.67
     wireType
    0.66
    JspWriter
    0.65
     betweenstory
    0.65
    Activations Density 1.956%

    No Known Activations