© 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. 22-GEMMASCOPE-RES-16K
    6. 9225
    Prev
    Next
    INDEX
    Explanations

    phrases that describe sharing personal narratives and storytelling through various mediums

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

    Appears after "via" or "through"

    np_acts-logits-general · gemini-2.0-flash

    media types or forms of expression

    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
    DockStyle
    -0.78
    fromnode
    -0.73
     nahilalakip
    -0.64
    RectangleBorder
    -0.61
    wpi
    -0.60
     wireType
    -0.57
     Exacts
    -0.57
    المراجع
    -0.56
    Искәрмәләр
    -0.56
     الرياضيه
    -0.55
    POSITIVE LOGITS
     visual
    1.55
     visuals
    1.50
    visual
    1.27
     pictorial
    1.27
     VISUAL
    1.17
     audiovisual
    1.16
    Visual
    1.13
     Visual
    1.10
     images
    1.10
     pictures
    1.10
    Activations Density 0.371%

    No Known Activations