© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3815
    Prev
    Next
    INDEX
    Explanations

    code involving output generation and data handling in programming

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

    Code snippets with HTML tags

    np_acts-logits-general · gemini-2.0-flash

    html tag or string literal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.95
    Koordinaten
    -0.92
     onCancelled
    -0.86
     myſelf
    -0.83
    ſelves
    -0.81
    Rhestr
    -0.80
     Мексичка
    -0.79
    jaardag
    -0.78
    +#+#
    -0.77
     ContentValues
    -0.76
    POSITIVE LOGITS
     '<
    1.35
     "<
    1.30
    '<
    1.15
    ("<
    1.05
    "<
    1.05
    ('<
    1.03
    ="<
    0.89
     `<
    0.88
    }<
    0.80
    "><
    0.79
    Activations Density 0.057%

    No Known Activations