© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102399
    Prev
    Next
    INDEX
    Explanations

    technical and programming-related terminology, particularly in API and framework contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.75
    MessageTagHelper
    -0.73
    FunctionFlags
    -0.71
     Roskov
    -0.70
    UnusedPrivate
    -0.68
    RuleContext
    -0.66
    expandindo
    -0.65
    contentLoaded
    -0.65
    Personendaten
    -0.65
     onCreateView
    -0.64
    POSITIVE LOGITS
     externo
    0.40
     sebou
    0.37
    spół
    0.37
     všem
    0.37
     Kartoff
    0.37
     paard
    0.36
     Erstellung
    0.36
     Spazier
    0.36
     ciała
    0.35
     sebagaimana
    0.35
    Activations Density 0.122%

    No Known Activations