© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13569
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical conditions, treatments, and biological processes

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

    First part of unusual words

    np_acts-logits-general · gemini-2.0-flash

    mucilliary, Lehmann, Cyclamate, Ankman, chemoprophylaxis, indemnification, surfworks, stabilises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ی
    -0.90
    zelfde
    -0.88
    י
    -0.78
    ième
    -0.77
    iyle
    -0.76
     Wikiseite
    -0.76
    y
    -0.75
    sweise
    -0.74
    ه
    -0.74
     wikipagina
    -0.73
    POSITIVE LOGITS
    <bos>
    1.88
    Ayy
    0.62
    mens
    0.60
    yszer
    0.57
    foli
    0.57
    vény
    0.56
    hob
    0.56
    cob
    0.56
    JKLM
    0.56
    ekš
    0.55
    Activations Density 6.707%

    No Known Activations