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. 6518
    Prev
    Next
    INDEX
    Explanations

    code structures and programming constructs related to functions and method implementations in Swift

    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
     betweenstory
    -0.44
     media
    -0.39
    tonode
    -0.38
    bootstrapcdn
    -0.38
     jsPsych
    -0.36
    meist
    -0.35
     league
    -0.35
     League
    -0.35
    .*")]
    -0.35
     Media
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.77
     gyhoeddwyd
    0.68
    :✨
    0.65
     nahilalakip
    0.64
     Chwiliwch
    0.58
     CreateTagHelper
    0.56
     مشين
    0.55
     חיצוניים
    0.54
     indisponible
    0.54
     Unavailable
    0.53
    Activations Density 0.541%

    No Known Activations