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. 31-GEMMASCOPE-RES-16K
    6. 15431
    Prev
    Next
    INDEX
    Explanations

    numerical and mathematical expressions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers after periods or exponents

    np_acts-logits-general · gemini-2.0-flash

    mathematical or code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.56
     BrowserModule
    -0.56
    URLException
    -0.54
    Literatuur
    -0.51
    providedIn
    -0.50
    affaires
    -0.49
    colnshire
    -0.49
    ölkerung
    -0.49
    peteer
    -0.49
    BitmapFactory
    -0.47
    POSITIVE LOGITS
    蚪
    0.40
    GEBURTSDATUM
    0.39
    1
    0.36
     correctes
    0.34
     thing
    0.34
    ☝
    0.34
    mbrie
    0.33
     monasterio
    0.32
     BoxFit
    0.31
     Utama
    0.30
    Activations Density 0.743%

    No Known Activations