© 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. 22-GEMMASCOPE-RES-16K
    11. 8305
    Prev
    Next
    INDEX
    Explanations

    Java method calls related to system output

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

    "System.out.println" calls

    np_acts-logits-general · gemini-2.0-flash

    System.out.println statements

    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
     fallu
    -0.58
     steckt
    -0.52
    antaranya
    -0.49
    urlpatterns
    -0.49
     including
    -0.48
     guère
    -0.48
     anzunehmen
    -0.48
    ³.
    -0.46
    StoryboardSegue
    -0.46
     blevet
    -0.46
    POSITIVE LOGITS
    out
    0.64
     System
    0.64
    OrBuilder
    0.63
     LoggerFactory
    0.62
    äft
    0.61
    iedenen
    0.60
    System
    0.60
    RectangleBorder
    0.60
     &___
    0.60
     Properties
    0.60
    Activations Density 0.019%

    No Known Activations