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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 3149
    Prev
    Next
    INDEX
    Explanations

    transitional phrases indicating a sequence of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "then"

    np_acts-logits-general · gemini-2.0-flash

    then followed by subsequent action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    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
    -0.80
    ).]
    -0.79
     himſelf
    -0.78
     Ophelia
    -0.78
     Harlow
    -0.77
    ilíbrio
    -0.77
     LoggerFactory
    -0.74
    randomUUID
    -0.73
     Winfrey
    -0.72
     themſelves
    -0.72
    POSITIVE LOGITS
    vdash
    0.65
    clearly
    0.62
     maybe
    0.62
     lintas
    0.61
     THEN
    0.61
     Dann
    0.60
    chitis
    0.60
    BackStack
    0.60
    emons
    0.59
    Elen
    0.57
    Activations Density 0.117%

    No Known Activations