© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8715
    Prev
    Next
    INDEX
    Explanations

    references to Android programming components and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.50
     Мексичка
    -0.32
    ContentLoaded
    -0.32
     imaginación
    -0.30
     android
    -0.29
     darah
    -0.29
     gereja
    -0.28
     hermana
    -0.28
    gewiesen
    -0.28
     família
    -0.28
    POSITIVE LOGITS
     initComponents
    0.88
    MigrationBuilder
    0.72
    Lähteet
    0.68
     CreateTagHelper
    0.63
     surla
    0.63
    wiſe
    0.58
     itſelf
    0.58
    leſs
    0.57
    muka
    0.57
     ſeveral
    0.56
    Activations Density 0.109%

    No Known Activations