© 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 - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 16037
    Prev
    Next
    INDEX
    Explanations

    details related to artistic modeling and crafting techniques

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

    Preceding numbers, or "crew" of something

    np_acts-logits-general · gemini-2.0-flash

    model modelmodel kit crew and parts

    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
    aringan
    -0.62
     olympiques
    -0.61
     olympique
    -0.53
     financières
    -0.53
    ivasan
    -0.52
     térm
    -0.50
     يتيمه
    -0.49
    retur
    -0.49
     culturelles
    -0.49
    uxxxx
    -0.48
    POSITIVE LOGITS
     kit
    1.00
     kits
    0.91
     scale
    0.88
     Scale
    0.85
     styrene
    0.84
     modeller
    0.83
     modell
    0.82
     decals
    0.81
    kit
    0.77
     resin
    0.77
    Activations Density 0.068%

    No Known Activations