© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 67423
    Prev
    Next
    INDEX
    Explanations

    references to specific species and formal taxonomic classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    species and subspecies naming

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ſche
    -0.84
     purpoſe
    -0.82
     pleaſure
    -0.81
     ſte
    -0.76
     juſ
    -0.70
     ſtand
    -0.67
     houſe
    -0.67
     Chriftian
    -0.65
     verſ
    -0.65
     faſt
    -0.61
    POSITIVE LOGITS
     anzunehmen
    0.43
     feminina
    0.41
     Parece
    0.40
     masculinos
    0.40
     senhora
    0.40
     demikian
    0.39
     tampaknya
    0.39
     alfombra
    0.38
     solitario
    0.38
     berdua
    0.38
    Activations Density 0.056%

    No Known Activations