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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8907
    Prev
    Next
    INDEX
    Explanations

    items related to arts and crafts

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

    before adjectives

    np_acts-logits-general · gemini-2.0-flash

    enamel pastry, decorative statement, American muscle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.60
    +:+
    -0.59
    migrationBuilder
    -0.58
    λώ
    -0.54
     bleek
    -0.54
    twimg
    -0.53
     pinulongan
    -0.53
     AssemblyCompany
    -0.52
    WindowListener
    -0.51
    IsMutable
    -0.49
    POSITIVE LOGITS
     early
    0.61
     late
    0.56
    early
    0.55
     étui
    0.53
     curiosity
    0.53
     frühen
    0.53
     Meiji
    0.52
    EARLY
    0.52
     famille
    0.51
     gué
    0.50
    Activations Density 0.143%

    No Known Activations