© 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. 102430
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials and data availability in academic writing

    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
     zove
    -0.36
    delwed
    -0.28
    cpus
    -0.27
    จัง
    -0.27
     marad
    -0.27
     sebagainya
    -0.26
     Anyways
    -0.26
     Gies
    -0.26
     Persson
    -0.26
     cidad
    -0.25
    POSITIVE LOGITS
     esternos
    0.71
    StoryboardSegue
    0.61
    ChildScrollView
    0.60
     nahilalakip
    0.60
     שוליים
    0.59
     lenker
    0.59
     wiſſen
    0.59
    fjspx
    0.58
     beſch
    0.58
    ロウィン
    0.58
    Activations Density 0.343%

    No Known Activations