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. 6451
    Prev
    Next
    INDEX
    Explanations

    coding terminologies and elements related to programming and data structures

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

    "G" followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    g or G in code contexts

    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
    المناصب
    -0.46
    Tembelea
    -0.46
     judiciales
    -0.44
    KURZBESCHREIBUNG
    -0.44
    ссажи
    -0.41
     незавершена
    -0.40
     Grenzen
    -0.40
     sintética
    -0.40
     Janssen
    -0.39
     rodilla
    -0.39
    POSITIVE LOGITS
     G
    1.53
    G
    1.52
     g
    1.35
    g
    1.25
    G
    1.09
    GG
    0.85
     GG
    0.84
     Г
    0.83
    g
    0.81
    Gs
    0.81
    Activations Density 0.757%

    No Known Activations