© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12496
    Prev
    Next
    INDEX
    Explanations

    phrases related to effectiveness and performance in a context, particularly in sports or competition

    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
     protoimpl
    -0.59
     CreateTagHelper
    -0.59
    Демографія
    -0.56
    webElementXpaths
    -0.54
    awtextra
    -0.51
    цездатний
    -0.51
    ValueStyle
    -0.49
    stylers
    -0.48
    migrationBuilder
    -0.48
     ModelExpression
    -0.48
    POSITIVE LOGITS
     ,
    2.22
     .
    1.58
     ،
    1.52
     ,
    1.44
     ，
    1.38
     .”
    1.38
     )
    1.36
     ;
    1.36
     ).
    1.34
     .)
    1.30
    Activations Density 1.376%

    No Known Activations