© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11651
    Prev
    Next
    INDEX
    Explanations

    elements from programming-related syntax and structure

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

    LaTeX math mode

    np_acts-logits-general · gemini-2.0-flash

    mathematical or code syntax

    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
     arşivlendi
    -0.61
     $($
    -0.52
     nakalista
    -0.48
     StringTokenizer
    -0.48
     ditto
    -0.46
    orla
    -0.46
    idom
    -0.45
    [_
    -0.45
     $(\
    -0.45
     numberOfRows
    -0.44
    POSITIVE LOGITS
    BeginContext
    0.91
    calipsis
    0.67
    出版年
    0.62
    "](
    0.60
     createSprite
    0.58
    RegressionTest
    0.57
     étoit
    0.55
    észetes
    0.54
     ResponseEntity
    0.54
    />";
    0.53
    Activations Density 2.512%

    No Known Activations