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. 22-GEMMASCOPE-RES-16K
    6. 13062
    Prev
    Next
    INDEX
    Explanations

    references to vehicle collisions and related terminology

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

    Comes before numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    United States of America

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &[
    -0.48
     itſelf
    -0.48
    .[/
    -0.48
     Anſ
    -0.47
     ſch
    -0.47
    &
    -0.46
     Efq
    -0.42
     ſhe
    -0.42
     Diſ
    -0.41
     paw
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    1.01
     nakalista
    1.00
     NSCoder
    0.92
    LabelTagHelper
    0.88
    MigrationBuilder
    0.87
    \}
    0.86
    featureID
    0.84
     تانيه
    0.83
     $\
    0.81
     \}
    0.81
    Activations Density 0.124%

    No Known Activations