© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 116081
    Prev
    Next
    INDEX
    Explanations

    terms related to geometric shapes, specifically cones

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

    cone or cones

    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
    кобрита
    -0.44
     Wil
    -0.37
    Barbados
    -0.37
     Phys
    -0.36
     SAV
    -0.36
     Capt
    -0.35
    Statics
    -0.35
    Affirmed
    -0.35
     Liv
    -0.35
    Alicia
    -0.35
    POSITIVE LOGITS
     Cone
    1.05
    Cone
    1.04
     cone
    1.04
    cone
    1.02
     cones
    0.80
     Houſe
    0.73
     Dome
    0.72
    cones
    0.67
    complexContent
    0.67
    Dome
    0.66
    Activations Density 0.015%

    No Known Activations