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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 4853
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and references in biological and genetic contexts

    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
     έκ
    -0.42
     unmute
    -0.42
     TextAppearance
    -0.41
    asteroide
    -0.41
     unknownFields
    -0.40
    rille
    -0.40
    ⊝
    -0.40
    arkhand
    -0.40
     Staple
    -0.40
     ple
    -0.39
    POSITIVE LOGITS
     begge
    0.68
     båda
    0.67
     keduanya
    0.66
     entrambi
    0.62
     both
    0.61
     beide
    0.61
    どちらも
    0.59
     beiden
    0.58
     Beide
    0.58
    both
    0.57
    Activations Density 0.176%

    No Known Activations