© 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. 38-GEMMASCOPE-RES-16K
    11. 7514
    Prev
    Next
    INDEX
    Explanations

    structured data elements, likely in a programming or data analysis context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.78
     تضيفلها
    -0.74
    AddTagHelper
    -0.73
     itſelf
    -0.66
     indígen
    -0.66
    ſelf
    -0.65
     pinulongan
    -0.65
    LookAnd
    -0.64
     الرياضيه
    -0.63
    leſs
    -0.63
    POSITIVE LOGITS
     xxxx
    0.40
    xxxx
    0.35
    同年
    0.33
     Superior
    0.32
     later
    0.32
     Ann
    0.31
    *******
    0.31
    XXXXX
    0.31
     】
    0.31
    Javadoc
    0.31
    Activations Density 1.171%

    No Known Activations