© 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. 25-GEMMASCOPE-RES-16K
    11. 15575
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to functions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wiss
    -0.39
     Inter
    -0.36
     actually
    -0.36
     lat
    -0.36
     da
    -0.36
     Whi
    -0.36
    ModelAndView
    -0.35
    issens
    -0.34
    jScrollPane
    -0.34
     retrou
    -0.34
    POSITIVE LOGITS
    parsedMessage
    0.70
     zijne
    0.59
    RenderAtEndOf
    0.55
     Wikimédia
    0.54
    hoeddwyd
    0.52
     المعيارى
    0.52
     Normdatei
    0.52
     CURIAM
    0.51
    InputBorder
    0.50
     navideñas
    0.50
    Activations Density 1.827%

    No Known Activations