© 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. 21-GEMMASCOPE-RES-16K
    6. 6222
    Prev
    Next
    INDEX
    Explanations

    specific attributes related to safety equipment or protective gear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autique
    -0.63
    WarningLevel
    -0.62
    ьаж
    -0.56
     circadian
    -0.54
     pistons
    -0.52
    contentLoaded
    -0.51
     aigu
    -0.51
     undef
    -0.51
    oules
    -0.50
     culvert
    -0.50
    POSITIVE LOGITS
     grip
    1.68
     grips
    1.44
     Grip
    1.41
    grip
    1.39
     hold
    1.38
    Grip
    1.30
     gripped
    1.25
     gripping
    1.23
    hold
    1.22
     holds
    1.20
    Activations Density 0.209%

    No Known Activations