© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    references to print-related processes or software functions

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

    Code, printing, or output-related actions

    np_acts-logits-general · gemini-2.0-flash

    printing and printed output

    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
    WriteBarrier
    -0.59
    клопе
    -0.56
     оригіналу
    -0.56
     мәкал
    -0.54
    quelize
    -0.53
    InputBorder
    -0.53
    ICAGO
    -0.52
    styleable
    -0.52
     '{@
    -0.52
    NOPQRST
    -0.50
    POSITIVE LOGITS
     print
    3.89
    print
    3.56
     Print
    3.31
    Print
    3.09
     printing
    2.95
     prints
    2.95
     PRINT
    2.85
     printed
    2.80
    PRINT
    2.64
     Printing
    2.56
    Activations Density 0.097%

    No Known Activations