© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5947
    Prev
    Next
    INDEX
    Explanations

    references to scientific documents and data related to health and treatment studies

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

    URLs, especially to PDFs or specific files

    np_acts-logits-general · gemini-2.0-flash

    URLs and file paths

    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
     wenige
    -0.37
     wenigen
    -0.35
     mengganggu
    -0.35
     memerlukan
    -0.33
    limiento
    -0.33
     olvidar
    -0.33
    tamientos
    -0.33
     menghasilkan
    -0.33
     melindungi
    -0.32
     melibatkan
    -0.32
    POSITIVE LOGITS
    WebServlet
    0.79
    ftagPool
    0.78
    ThroughAttribute
    0.78
    ConstraintMaker
    0.74
    styleable
    0.66
     EconPapers
    0.64
     Taktlose
    0.63
    verwijspagina
    0.62
    MLLoader
    0.61
    fromnode
    0.59
    Activations Density 0.767%

    No Known Activations