© 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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1369
    Prev
    Next
    INDEX
    Explanations

    descriptions of food items and their preparation

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

    food items and dishes, particularly those related to Jamaican cuisine

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

    sides and accompaniments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    +#+#
    -0.81
    IUrlHelper
    -0.72
     nakalista
    -0.68
    AddHtmlAttribute
    -0.66
    verifyException
    -0.64
    SharedCtor
    -0.63
    afficheront
    -0.63
     Roskov
    -0.63
    Jeografia
    -0.61
    IntoConstraints
    -0.61
    POSITIVE LOGITS
     side
    0.93
     sides
    0.85
     Side
    0.74
     bebida
    0.72
    Side
    0.71
     SIDE
    0.71
     accompanying
    0.70
     drink
    0.68
     drinks
    0.67
     salad
    0.65
    Activations Density 0.060%

    No Known Activations