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. 8649
    Prev
    Next
    INDEX
    Explanations

    instances of programming-related elements and structures, particularly those relating to weather data management and APIs

    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
     lleno
    -0.31
     społecz
    -0.29
     פני
    -0.28
     sombra
    -0.27
     Erde
    -0.27
    ROOT
    -0.26
    über
    -0.26
     humaine
    -0.26
    September
    -0.26
    ณา
    -0.26
    POSITIVE LOGITS
    IntoConstraints
    1.08
     disambiguazione
    0.92
     AssemblyCulture
    0.90
    Personendaten
    0.85
     الرياضيه
    0.84
     للاسماء
    0.84
    ChildScrollView
    0.83
    tagHelperRunner
    0.82
    principalColumn
    0.82
    Personensuche
    0.78
    Activations Density 0.518%

    No Known Activations