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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 3246
    Prev
    Next
    INDEX
    Explanations

    technical details about transmission systems in vehicles

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

    Manual or automatic modes

    np_acts-logits-general · gemini-2.0-flash

    manual driving mode

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    PerformLayout
    -0.70
    Composable
    -0.62
    DataAnnotations
    -0.61
     kaarangay
    -0.59
     uſed
    -0.57
     becauſe
    -0.56
     whoſe
    -0.56
     houſe
    -0.55
     Avez
    -0.55
     himſelf
    -0.54
    POSITIVE LOGITS
     mode
    2.44
     Mode
    2.14
     modes
    2.05
    mode
    2.00
    Mode
    1.99
     MODE
    1.90
     Modes
    1.76
    MODE
    1.75
    modes
    1.67
    モード
    1.66
    Activations Density 0.327%

    No Known Activations