© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4348
    Prev
    Next
    INDEX
    Explanations

    mentions of materials and their properties or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -1.03
     calendriers
    -0.94
     تضيفلها
    -0.92
     perist
    -0.89
     uncin
    -0.88
     sequestration
    -0.88
     Pseudomonas
    -0.85
    Hochspringen
    -0.84
    Попис
    -0.84
     propOrder
    -0.83
    POSITIVE LOGITS
     material
    1.77
     materials
    1.76
     Material
    1.63
     Materials
    1.55
    MATERIAL
    1.53
    materials
    1.53
    material
    1.50
     MATERIAL
    1.50
    Materials
    1.49
    Material
    1.47
    Activations Density 0.090%

    No Known Activations