Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4496
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering processes and components

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

    Parts of machines or structures

    np_acts-logits-general · gemini-2.0-flash

    physical components

    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
    Personensuche
    -0.76
     kasarigan
    -0.72
     estekak
    -0.69
    ConstraintMaker
    -0.68
    PerformLayout
    -0.67
     propOrder
    -0.63
    adaptiveStyles
    -0.63
     NSCoder
    -0.62
     muualla
    -0.62
    Revenir
    -0.61
    POSITIVE LOGITS
     body
    0.94
     itself
    0.88
     periphery
    0.79
     walls
    0.74
     surface
    0.74
     wall
    0.72
     region
    0.72
     edge
    0.69
     core
    0.68
     structure
    0.68
    Activations Density 1.204%

    No Known Activations