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. 38922
    Prev
    Next
    INDEX
    Explanations

    terms associated with financial transactions and obligations

    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
    AccessorTable
    -0.49
    adaptiveStyles
    -0.48
     tallas
    -0.41
     porcelaine
    -0.38
     индивиду
    -0.38
    providedIn
    -0.38
    ądź
    -0.38
     nasional
    -0.37
     masculina
    -0.37
    čki
    -0.37
    POSITIVE LOGITS
    LEncoder
    0.48
    ➌
    0.46
     NUKAT
    0.44
     Réponses
    0.44
     يتيمه
    0.43
    setupUi
    0.39
     TextEditing
    0.39
     OOO
    0.39
    ltk
    0.39
     الحره
    0.39
    Activations Density 0.008%

    No Known Activations