© 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. 14928
    Prev
    Next
    INDEX
    Explanations

    programming or coding constructs, specifically related to function definitions and flow control statements

    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
    脚注の使い方
    -0.95
     informée
    -0.75
     Waſſer
    -0.74
    NameInMap
    -0.72
     ſind
    -0.71
    styleType
    -0.71
     AttributeSet
    -0.70
     esternos
    -0.70
     $_"
    -0.69
    parsedMessage
    -0.69
    POSITIVE LOGITS
     ->
    0.46
     //
    0.43
     :
    0.42
     @
    0.40
     |
    0.40
    ::
    0.40
     =
    0.39
    ->
    0.38
    \[
    0.38
     #
    0.38
    Activations Density 3.493%

    No Known Activations