© 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. 12-GEMMASCOPE-RES-16K
    11. 11437
    Prev
    Next
    INDEX
    Explanations

    the word 'which' in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Olms
    -0.69
    ed
    -0.67
     Juneau
    -0.67
    ded
    -0.66
    cy
    -0.63
     Baton
    -0.63
     Coss
    -0.62
     Magee
    -0.61
     Folsom
    -0.60
     Hov
    -0.60
    POSITIVE LOGITS
     WHICH
    1.25
     Which
    1.24
    Which
    1.17
    which
    1.14
     which
    1.13
     wich
    1.11
    Datuak
    1.09
    ]**
    1.05
    ']))
    1.04
    hich
    0.96
    Activations Density 0.153%

    No Known Activations