© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 58716
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and forms

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

    round circular shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.43
     définiti
    -0.38
    horabuena
    -0.38
     оригіналу
    -0.37
     trekken
    -0.37
     néglig
    -0.37
     giudi
    -0.37
    Jud
    -0.37
    Pep
    -0.36
     gynhyrchwyd
    -0.36
    POSITIVE LOGITS
     circular
    0.85
     round
    0.83
     circle
    0.80
     square
    0.77
     Circular
    0.75
     Round
    0.74
     Diameter
    0.73
     круг
    0.72
     Circle
    0.71
     circles
    0.70
    Activations Density 0.127%

    No Known Activations