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. 21-GEMMASCOPE-RES-16K
    6. 12637
    Prev
    Next
    INDEX
    Explanations

    concepts related to research networking and harmonization across studies

    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
    новништво
    -0.37
     الرياضيه
    -0.37
    vdash
    -0.37
    xane
    -0.36
    Microkernel
    -0.35
     Leck
    -0.33
    paddingRight
    -0.33
     bre
    -0.33
     Dray
    -0.33
     righe
    -0.32
    POSITIVE LOGITS
    统一
    0.87
     seragam
    0.86
     einheit
    0.83
     uniformity
    0.82
    共通
    0.80
     standardize
    0.80
     standardi
    0.79
     unified
    0.78
     uniform
    0.77
    統一
    0.76
    Activations Density 1.119%

    No Known Activations