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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15588
    Prev
    Next
    INDEX
    Explanations

    units of measurement related to weight and mass

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.82
    Искәрмәләр
    -0.67
    Vezi
    -0.66
    клопе
    -0.59
     InputDecoration
    -0.59
    ousing
    -0.58
     kaynağından
    -0.58
    +#+#
    -0.57
    Архівовано
    -0.55
     nahilalakip
    -0.55
    POSITIVE LOGITS
     pounds
    1.34
     weight
    1.32
     kilos
    1.20
     kg
    1.19
    weight
    1.19
     kilogram
    1.18
     weights
    1.17
     kilograms
    1.16
     lbs
    1.15
    Weight
    1.13
    Activations Density 0.280%

    No Known Activations