© 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 EvalsExportsinterp-engineNEWAPI 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. 8615
    Prev
    Next
    INDEX
    Explanations

    indications of medical conditions related to sleep disorders and their implications

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

    that can precede a comma

    np_acts-logits-general · gemini-2.0-flash

    sometimes

    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
    Hentet
    -0.52
    BagLayout
    -0.44
    URLEncoder
    -0.44
    swire
    -0.43
    접
    -0.42
    RenderAtEndOf
    -0.42
    anaf
    -0.41
    ansch
    -0.41
     aran
    -0.40
    etna
    -0.39
    POSITIVE LOGITS
     sometimes
    0.89
     parfois
    0.78
     fometimes
    0.74
     Sometimes
    0.70
    有时候
    0.69
    Sometimes
    0.69
     quelquefois
    0.68
     ممکن
    0.67
    有時
    0.66
     bazen
    0.66
    Activations Density 0.858%

    No Known Activations