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. 9-GEMMASCOPE-RES-16K
    6. 3764
    Prev
    Next
    INDEX
    Explanations

    components and technical elements in programming code

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

    "current" or "voltage" and related measurements

    np_acts-logits-general · gemini-2.0-flash

    electrical current and voltage characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     account
    -0.31
     PLWABN
    -0.30
     Einsch
    -0.30
     ponta
    -0.28
    contrib
    -0.28
     Cuenta
    -0.28
    Distribuzione
    -0.28
    ie
    -0.26
     saman
    -0.26
     Langen
    -0.26
    POSITIVE LOGITS
     StatelessWidget
    0.88
     المعيارى
    0.82
     ſind
    0.81
     ddelwed
    0.74
    Personensuche
    0.73
     nahilalakip
    0.72
     StatefulWidget
    0.71
    nextProps
    0.70
     propTypes
    0.69
     geſ
    0.69
    Activations Density 0.449%

    No Known Activations