© 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. 4157
    Prev
    Next
    INDEX
    Explanations

    inquiries seeking assistance or clarifications regarding technical issues

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

    Following verbs such as "to", "help", "find"

    np_acts-logits-general · gemini-2.0-flash

    to find or help

    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
     disambiguazione
    -0.83
     ویکی‌پدی
    -0.79
    httphttps
    -0.77
    Autoritní
    -0.71
    GEBURTSDATUM
    -0.71
    parsedMessage
    -0.71
    EndProject
    -0.70
     autorytatywna
    -0.69
    Personensuche
    -0.68
     snippetHide
    -0.68
    POSITIVE LOGITS
    EntityFramework
    0.29
    <eos>
    0.27
    ga
    0.24
     ++;
    0.24
     sür
    0.23
     थ
    0.23
    usammen
    0.22
     témoignage
    0.22
     пото
    0.22
    )));
    0.21
    Activations Density 0.850%

    No Known Activations