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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2049
    Prev
    Next
    INDEX
    Explanations

    specific names, titles, and codes related to scientific research and experimentation

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

    Appears before foreign names or terms

    np_acts-logits-general · gemini-2.0-flash

    "Barnett" and "瑞恵"

    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
    \,.
    -0.58
    access
    -0.58
    \,,
    -0.57
     vistazo
    -0.57
     access
    -0.57
     lyst
    -0.56
    Loren
    -0.54
    TextHelper
    -0.53
     to
    -0.51
    bootstrapcdn
    -0.51
    POSITIVE LOGITS
    expandindo
    0.55
    DockStyle
    0.54
     Jaguar
    0.51
     CanadaChoose
    0.50
     Colgate
    0.50
     defStyle
    0.50
     Wilkinson
    0.48
    authToken
    0.48
     jaguar
    0.48
     startX
    0.48
    Activations Density 2.325%

    No Known Activations