© 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. 7076
    Prev
    Next
    INDEX
    Explanations

    referring expressions and spatial relationships within the text

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

    Following "the" to indicate a location

    np_acts-logits-general · gemini-2.0-flash

    sports positions

    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
    IsContent
    -0.72
    AndEndTag
    -0.61
    ctime
    -0.55
     comune
    -0.55
    Tikang
    -0.53
     nakalista
    -0.53
    もしれません
    -0.52
    ModelState
    -0.52
    LikeLiked
    -0.52
    setVerticalGroup
    -0.52
    POSITIVE LOGITS
     opposition
    0.69
     box
    0.61
    opposition
    0.58
     opponents
    0.57
    (!__
    0.56
    opposed
    0.56
     visitors
    0.55
     opponent
    0.54
     paint
    0.54
    IUrlHelper
    0.53
    Activations Density 0.112%

    No Known Activations