© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14270
    Prev
    Next
    INDEX
    Explanations

    keywords related to configuration settings in programming, particularly for debugging and environment setup

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

    "Debug" or "Production" mode settings

    np_acts-logits-general · gemini-2.0-flash

    debug and environment modes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     nahilalakip
    -0.55
    verwijspagina
    -0.53
    ftagPool
    -0.52
     autorytatywna
    -0.52
    tagHelperRunner
    -0.52
    новниш
    -0.50
    fjspx
    -0.49
     utafitiHapana
    -0.49
    OrBuilder
    -0.48
     informée
    -0.48
    POSITIVE LOGITS
    Debug
    0.46
     Debug
    0.43
    debug
    0.41
    BuildConfig
    0.41
     NDEBUG
    0.40
     DEBUG
    0.38
     debug
    0.38
    DEBUG
    0.36
     palvel
    0.36
     Environment
    0.34
    Activations Density 0.146%

    No Known Activations