© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3880
    Prev
    Next
    INDEX
    Explanations

    metadata related to time or editing history

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

    Time or ID with "5" following "1" in a sequence

    np_acts-logits-general · gemini-2.0-flash

    digits starting with 15

    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
    DockStyle
    -0.81
    IUrlHelper
    -0.77
    InitVars
    -0.76
     AssemblyTitle
    -0.71
    riwal
    -0.68
     Braille
    -0.68
     CreateTagHelper
    -0.66
    mphony
    -0.64
     centrifugal
    -0.64
     surnames
    -0.62
    POSITIVE LOGITS
    timestamp
    0.40
    tså
    0.40
    providedIn
    0.39
    strtotime
    0.39
     strtotime
    0.36
     Chim
    0.36
     parem
    0.36
    Timestamp
    0.36
    vestido
    0.35
     Timestamp
    0.35
    Activations Density 0.227%

    No Known Activations