© 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. 101701
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
     strongest
    -0.38
    ura
    -0.34
    strong
    -0.33
    AntiForgeryToken
    -0.33
    strongly
    -0.32
    rem
    -0.32
    acce
    -0.32
    base
    -0.31
     مض
    -0.31
    SizeF
    -0.31
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.55
     للاسماء
    0.55
     оригіналу
    0.54
    Portail
    0.53
    asteroide
    0.52
    ecutive
    0.50
    Personensuche
    0.50
    ⟭
    0.50
    hoeddwyd
    0.50
     autorytatywna
    0.49
    Activations Density 0.020%

    No Known Activations