© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9466
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    Email addresses

    np_acts-logits-general · gemini-2.0-flash

    email addresses and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.95
     виправивши
    -0.80
    ViewFeatures
    -0.80
    RenderAtEndOf
    -0.72
    aarrggbb
    -0.71
     للاسماء
    -0.68
    kloped
    -0.66
     متعلقه
    -0.66
    ValueStyle
    -0.65
    AnchorStyles
    -0.64
    POSITIVE LOGITS
    gmail
    1.34
    hotmail
    1.04
    yahoo
    0.98
     gmail
    0.97
    mail
    0.89
     email
    0.80
    Gmail
    0.79
    outlook
    0.72
     yahoo
    0.71
    email
    0.70
    Activations Density 0.046%

    No Known Activations