© 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. 39-GEMMASCOPE-RES-16K
    11. 1150
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to programming, specifically generic types and interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.63
    FieldOffsetTable
    -0.61
     estekak
    -0.54
     Италијани
    -0.52
     مرئيه
    -0.47
    yya
    -0.47
    PMailer
    -0.47
    verifyException
    -0.46
     betweenstory
    -0.45
    abestanden
    -0.45
    POSITIVE LOGITS
     generic
    0.63
     types
    0.60
     Typen
    0.59
     subtypes
    0.57
     tipos
    0.52
    generic
    0.51
    elementType
    0.50
     gener
    0.50
     compatible
    0.49
     typeof
    0.49
    Activations Density 0.911%

    No Known Activations