© 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. 13325
    Prev
    Next
    INDEX
    Explanations

    references to "Ca" or related variations, likely indicating a specific topic or theme associated with that term

    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
     smart
    -0.38
    ⓧ
    -0.36
    Intended
    -0.36
    protobuf
    -0.34
     dimaksud
    -0.34
     vision
    -0.33
     Vogel
    -0.32
    timo
    -0.31
     bug
    -0.31
     intended
    -0.30
    POSITIVE LOGITS
    RTSC
    0.65
     Савезне
    0.60
     resourceCulture
    0.59
     snippetHide
    0.59
    ViewImports
    0.56
    脚注の使い方
    0.55
    XmlAccessType
    0.54
    ftagPool
    0.54
     estekak
    0.54
    MLLoader
    0.53
    Activations Density 0.283%

    No Known Activations