© 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. 18-GEMMASCOPE-RES-16K
    11. 1891
    Prev
    Next
    INDEX
    Explanations

    data structures or references that seem to indicate recordkeeping or statistical analysis

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

    Numbers followed by ': {'

    np_acts-logits-general · gemini-2.0-flash

    numbers and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chemise
    -0.48
    Bronnen
    -0.45
    RenderAtEndOf
    -0.45
    enio
    -0.43
     dente
    -0.43
    ami
    -0.43
     préparer
    -0.43
    createComponent
    -0.42
     dobles
    -0.41
     consultato
    -0.41
    POSITIVE LOGITS
     '\\;'
    0.72
    aarrggbb
    0.68
    HasAnnotation
    0.65
    Obrázky
    0.64
    hyrchwyd
    0.63
    wpi
    0.62
    InjectAttribute
    0.62
     Krakow
    0.60
    SBATCH
    0.57
     graduates
    0.57
    Activations Density 0.768%

    No Known Activations