© 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. 20-GEMMASCOPE-RES-16K
    11. 14773
    Prev
    Next
    INDEX
    Explanations

    technical language related to medical and scientific contexts

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

    Text after a hyphen or article

    np_acts-logits-general · gemini-2.0-flash

    binding, disease, roof, buckle, rigid, Decepticons

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    TagMode
    -0.44
     lenker
    -0.40
     Taktlose
    -0.39
     <>",
    -0.37
     <=",
    -0.36
     }{@
    -0.35
    protoimpl
    -0.34
    cstdlib
    -0.31
    paigns
    -0.31
    getKeyCode
    -0.30
    POSITIVE LOGITS
    tonode
    0.66
    хьтан
    0.65
    principalTable
    0.59
     المعيارى
    0.56
    Diweddarwch
    0.56
    Tembelea
    0.55
    Попис
    0.53
     Autorizaciones
    0.52
     Chwiliwch
    0.52
    <pad>
    0.51
    Activations Density 0.561%

    No Known Activations