© 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. 31-GEMMASCOPE-RES-16K
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    references to the "X" data format and related technologies

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

    the letter "X" followed by a hyphen and another word or number (X-ray, X-chromosome, X-query, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.41
    ViewFeatures
    -0.35
     Primary
    -0.34
    errHandler
    -0.32
     primary
    -0.32
     Figue
    -0.31
     Futter
    -0.30
    tetur
    -0.30
    AddHtmlAttribute
    -0.29
     חז
    -0.29
    POSITIVE LOGITS
     X
    0.69
     XB
    0.67
     getX
    0.61
     Xtreme
    0.61
     XE
    0.60
     XA
    0.59
     Xe
    0.59
     Xander
    0.59
     XC
    0.58
     XT
    0.58
    Activations Density 0.444%

    No Known Activations