© 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. 24-GEMMASCOPE-RES-16K
    11. 10442
    Prev
    Next
    INDEX
    Explanations

    discussions of responsibility and accountability in various contexts

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

    that follow commas

    np_acts-logits-general · gemini-2.0-flash

    but, nevertheless, still

    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
     للاسماء
    -0.85
     ویکی‌پدی
    -0.84
    quelize
    -0.83
    principalColumn
    -0.81
     propOrder
    -0.78
    новништво
    -0.78
    AddTagHelper
    -0.75
    Hentet
    -0.74
    webElementXpaths
    -0.73
    tagHelperRunner
    -0.71
    POSITIVE LOGITS
    but
    0.35
     aún
    0.34
     dennoch
    0.33
    others
    0.33
     إلا
    0.33
    iertamente
    0.32
     but
    0.32
    still
    0.31
     andererseits
    0.30
     nevertheless
    0.30
    Activations Density 0.267%

    No Known Activations