© 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. 20-GEMMASCOPE-RES-16K
    11. 98
    Prev
    Next
    INDEX
    Explanations

    control flow structures and function definitions in code

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

    Code snippets; error handling and logging

    np_acts-logits-general · gemini-2.0-flash

    logging and code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.61
    xmlhttp
    -0.52
     Chwiliwch
    -0.51
     onCreateView
    -0.49
     فض
    -0.48
     mögen
    -0.47
    jsoup
    -0.47
    =?";
    -0.44
    IntentFilter
    -0.43
    igten
    -0.43
    POSITIVE LOGITS
    console
    0.84
    print
    0.73
    qDebug
    0.71
    Log
    0.69
     console
    0.66
    NSLog
    0.64
    Logger
    0.64
     Logs
    0.63
    Slf
    0.63
    webElementXpaths
    0.61
    Activations Density 0.066%

    No Known Activations