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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16003
    Prev
    Next
    INDEX
    Explanations

    features and specifications of electronic devices, particularly related to audio and connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.62
    Diwedd
    -0.58
     Réponses
    -0.57
    Viitteet
    -0.55
    verwijspagina
    -0.55
     kaarangay
    -0.51
    bildēt
    -0.51
     समीक्षाओं
    -0.51
     مشين
    -0.50
     Wikispecies
    -0.49
    POSITIVE LOGITS
    PYX
    0.39
     <<<<<<<<<<<<<<
    0.38
    amazon
    0.34
     общем
    0.33
    Slf
    0.32
    hecho
    0.32
    nonatomic
    0.31
    amzn
    0.30
     ideal
    0.30
    isPresent
    0.30
    Activations Density 0.050%

    No Known Activations