Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53458
    Prev
    Next
    INDEX
    Explanations

    references to productivity and economic necessity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    findpost
    -0.47
     мәкал
    -0.45
     препратки
    -0.45
     EconPapers
    -0.44
     PopupWindow
    -0.43
     autorytatywna
    -0.43
    ChildScrollView
    -0.43
     HFILL
    -0.42
    unknownFields
    -0.42
     invokingState
    -0.42
    POSITIVE LOGITS
     neceſſ
    0.52
     purpoſe
    0.47
     Könige
    0.47
     ſta
    0.45
     ſol
    0.44
     precisión
    0.44
     eſt
    0.43
     houſe
    0.43
     hjælp
    0.42
     nødvendig
    0.42
    Activations Density 0.082%

    No Known Activations