© 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. 9031
    Prev
    Next
    INDEX
    Explanations

    specific terminology and jargon related to programming, mathematics, and scientific concepts

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

    Strings of letters and numbers

    np_acts-logits-general · gemini-2.0-flash

    ORB, abd, atl identifiers

    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
    sweise
    -0.82
    ième
    -0.79
    zelfde
    -0.73
    iyle
    -0.70
    ی
    -0.66
     Administrativna
    -0.64
     يتيمه
    -0.64
     miniaturka
    -0.63
    یتی
    -0.63
    iarkan
    -0.63
    POSITIVE LOGITS
    <bos>
    2.44
    yszer
    0.68
    pośred
    0.62
    ekš
    0.61
    してみて
    0.61
    vény
    0.60
    mens
    0.60
    himo
    0.60
     duyg
    0.60
    kozó
    0.60
    Activations Density 11.899%

    No Known Activations