© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6090
    Prev
    Next
    INDEX
    Explanations

    quantities and numerical data, including prices and statistics

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

    Numbers between 0 and 9

    np_acts-logits-general · gemini-2.0-flash

    numeric quantities with decimals

    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
     szóci
    -0.67
    }}^{(
    -0.63
    MENAFN
    -0.60
    webElementGuid
    -0.58
     ErrIntOverflow
    -0.58
    Geplaatst
    -0.58
    tvguidetime
    -0.57
     utafitiHapana
    -0.55
     autorytatywna
    -0.54
    UseVisualStyle
    -0.52
    POSITIVE LOGITS
    LEncoder
    0.77
     OPEC
    0.48
    contentLoaded
    0.47
    ünstler
    0.47
    Disaster
    0.47
    러나
    0.47
     समीक्षाओं
    0.46
     هيا
    0.45
    MLLoader
    0.44
    ScreenState
    0.44
    Activations Density 0.983%

    No Known Activations