© 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. 102364
    Prev
    Next
    INDEX
    Explanations

    evidence or validation related to hypotheses or claims

    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
    Бахар
    -0.51
     Samaria
    -0.50
    InputBorder
    -0.49
    Controlling
    -0.46
     Assemb
    -0.45
    ritsar
    -0.45
     toni
    -0.45
     assemb
    -0.45
     intervi
    -0.44
     ome
    -0.43
    POSITIVE LOGITS
     twier
    0.54
    sizeCache
    0.51
     belief
    0.48
     Behaup
    0.47
     pulseira
    0.47
     behaup
    0.46
     hipótesis
    0.46
     مشين
    0.45
     XCTest
    0.45
    retudo
    0.45
    Activations Density 0.087%

    No Known Activations