© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105005
    Prev
    Next
    INDEX
    Explanations

    terminologies related to software directives and environments

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zarchiwizowane
    -0.51
     <<<<<<<<<<<<<<
    -0.41
    脚注の使い方
    -0.41
    prepareStatement
    -0.38
     intStringLen
    -0.38
    Brainz
    -0.38
    ClCompile
    -0.36
    SELECTED
    -0.35
    Aktualisiert
    -0.34
     Backman
    -0.34
    POSITIVE LOGITS
    ExtendWith
    1.16
     resourceCulture
    0.62
    NameInMap
    0.60
    scalatest
    0.59
    RuleContext
    0.58
    Rule
    0.56
    SBATCH
    0.54
    Captor
    0.54
     للاسماء
    0.54
    tagHelperRunner
    0.51
    Activations Density 0.005%

    No Known Activations