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

    Neuronpedia

    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. 24-GEMMASCOPE-RES-16K
    11. 1626
    Prev
    Next
    INDEX
    Explanations

    technical jargon and specialized terms related to scientific or computational concepts

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

    Acronyms/initialisms

    np_acts-logits-general · gemini-2.0-flash

    USP, IOC, XP acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
    -0.86
    ième
    -0.86
     miniaturka
    -0.75
     Administrativna
    -0.71
     Grüsse
    -0.70
    ۰
    -0.70
     zijne
    -0.69
    iyle
    -0.69
     unterkunft
    -0.69
    ação
    -0.65
    POSITIVE LOGITS
    <bos>
    1.88
    してみて
    0.73
    yszer
    0.65
    cob
    0.64
    himo
    0.63
    묻
    0.63
    Kont
    0.60
    hamm
    0.60
    Ayy
    0.60
    nap
    0.59
    Activations Density 3.160%

    No Known Activations