© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 50517
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to experimental samples and their attributes

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

    patient 0, 1, 7, 100, 21, 33 codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antd
    -0.32
    stdc
    -0.30
     éto
    -0.30
     florales
    -0.26
     Heart
    -0.26
    GLY
    -0.25
     Foreign
    -0.25
     RST
    -0.25
    Wf
    -0.24
     الن
    -0.24
    POSITIVE LOGITS
    Tikang
    0.60
    orianCalendar
    0.59
    InjectAttribute
    0.59
    Демографія
    0.58
    endpush
    0.58
     AssemblyVersion
    0.58
     محفوظة
    0.57
    utilisons
    0.54
     تضيفلها
    0.54
    msgTypes
    0.54
    Activations Density 0.320%

    No Known Activations