© 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. 6355
    Prev
    Next
    INDEX
    Explanations

    details about measurements, particularly height and related numerical descriptions

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

    Measurements involving "feet" or "foot"

    np_acts-logits-general · gemini-2.0-flash

    six feet

    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
     ProtoMessage
    -0.71
     désolés
    -0.58
    webElementXpaths
    -0.57
    WRP
    -0.57
    AddTagHelper
    -0.56
    jspx
    -0.55
    MessageOf
    -0.55
    apimachinery
    -0.54
    ặng
    -0.54
    localctx
    -0.54
    POSITIVE LOGITS
     feet
    1.37
     foot
    1.32
    foot
    1.15
     FOOT
    1.07
     Foot
    1.00
    feet
    0.99
     FEET
    0.99
     Feet
    0.98
    Foot
    0.93
     pieds
    0.90
    Activations Density 0.123%

    No Known Activations