© 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. 16-GEMMASCOPE-RES-16K
    6. 1793
    Prev
    Next
    INDEX
    Explanations

    quantitative data, particularly involving numbers and statistics

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

    Numbers within mathematical or statistical contexts

    np_acts-logits-general · gemini-2.0-flash

    numbers before or after specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -0.62
     surla
    -0.61
    ☸
    -0.60
    NewUrlParser
    -0.60
    ⓧ
    -0.59
    脚注の使い方
    -0.59
    SourceChecksum
    -0.57
    addPreferredGap
    -0.56
    HasAnnotation
    -0.56
     transfieras
    -0.55
    POSITIVE LOGITS
    rungsseite
    0.75
    Становништво
    0.57
     itſelf
    0.56
     iſt
    0.55
     BoxDecoration
    0.55
     nonUne
    0.54
     isInitialized
    0.54
     Matériau
    0.53
     Majefty
    0.52
    IVEREF
    0.52
    Activations Density 1.045%

    No Known Activations