Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 7162
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Then" used to introduce or transition between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.77
     himſelf
    -0.76
     themſelves
    -0.75
     GenerationType
    -0.71
    randomUUID
    -0.71
    ilíbrio
    -0.70
     Irm
    -0.69
     Guggenheim
    -0.69
     Ophelia
    -0.69
     Majefty
    -0.68
    POSITIVE LOGITS
     THEN
    0.68
    emons
    0.67
    clearly
    0.65
    vdash
    0.64
    THEN
    0.64
     maybe
    0.64
     perhaps
    0.61
    cinta
    0.61
    สิน
    0.61
    れたら
    0.60
    Activations Density 0.105%

    No Known Activations