© 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. 1-GEMMASCOPE-RES-16K
    11. 6302
    Prev
    Next
    INDEX
    Explanations

    instances where "it" and variations of the word "do" are used in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.75
    তথ্যসূত্র
    -0.67
    Билгалдахарш
    -0.63
     kasarigan
    -0.61
    theless
    -0.61
    SharedCtor
    -0.61
     htons
    -0.61
    ^(@)
    -0.59
    ureusement
    -0.59
     OnTrigger
    -0.58
    POSITIVE LOGITS
    ubern
    0.56
    Doing
    0.55
    Does
    0.54
     doit
    0.53
    ())))
    0.52
     does
    0.51
    setopt
    0.51
     Does
    0.51
    läufe
    0.51
    doit
    0.50
    Activations Density 0.156%

    No Known Activations