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. 7723
    Prev
    Next
    INDEX
    Explanations

    clauses indicating conditions or relationships between elements in a statement

    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
    AnimationsModule
    -0.63
    rrggbb
    -0.60
     Waſſer
    -0.53
    +#+#
    -0.50
     المعيارى
    -0.49
    
    -0.49
    exitRule
    -0.49
    featureID
    -0.48
     dieſem
    -0.47
    CodeAttribute
    -0.47
    POSITIVE LOGITS
     löytyy
    0.41
     kuulu
    0.41
    navigateTo
    0.40
    defaults
    0.39
    guisement
    0.37
    pustakaan
    0.36
    éraire
    0.35
     cé
    0.35
     kereta
    0.35
    Hentet
    0.35
    Activations Density 1.220%

    No Known Activations