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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13753
    Prev
    Next
    INDEX
    Explanations

    functions related to image handling and storage in code

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

    Code snippets containing "print"

    np_acts-logits-general · gemini-2.0-flash

    code or legal language

    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
    oa̍t
    -0.63
    Chham
    -0.58
     aastal
    -0.57
    RTEX
    -0.56
    ValueStyle
    -0.55
    Portail
    -0.53
     Wikimedijinoj
    -0.52
    cima
    -0.52
    ReusableCell
    -0.51
     Мексичка
    -0.51
    POSITIVE LOGITS
    guard
    0.85
    print
    0.84
    let
    0.79
     print
    0.72
     guard
    0.72
    println
    0.65
    if
    0.61
     let
    0.59
    DispatchQueue
    0.59
     println
    0.57
    Activations Density 0.092%

    No Known Activations