© 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. 15440
    Prev
    Next
    INDEX
    Explanations

    phrases related to online purchasing and gambling

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

    Preceding special characters or uncommon words

    np_acts-logits-general · gemini-2.0-flash

    certain forward

    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
    IntoConstraints
    -0.99
    ValueStyle
    -0.89
    ConstraintMaker
    -0.86
    InjectAttribute
    -0.85
    WebVitals
    -0.80
     وتسجيلات
    -0.75
    بوابة
    -0.75
     فريبيس
    -0.72
    AnchorStyles
    -0.71
    ArgumentParser
    -0.70
    POSITIVE LOGITS
    ZZI
    0.50
    GETHER
    0.48
     dot
    0.46
    ġġ
    0.45
    byes
    0.44
     sample
    0.44
    ers
    0.44
    டன்
    0.43
     program
    0.43
     Trojans
    0.43
    Activations Density 0.039%

    No Known Activations