© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1403
    Prev
    Next
    INDEX
    Explanations

    phrases related to dark, dangerous, or mysterious scenarios

    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
     estekak
    -0.66
    UseVisualStyle
    -0.51
     surla
    -0.47
    ConstraintMaker
    -0.47
    setVerticalGroup
    -0.47
     الرياضيه
    -0.47
     jsPsych
    -0.44
    itinéraire
    -0.44
    RTEE
    -0.43
    Poloha
    -0.43
    POSITIVE LOGITS
     depths
    1.16
     darkness
    1.08
     wilderness
    1.05
     jungle
    1.02
     dark
    1.00
     abyss
    0.98
     woods
    0.95
     jungles
    0.95
     wilds
    0.91
     darkest
    0.90
    Activations Density 0.297%

    No Known Activations