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. 20-GEMMASCOPE-RES-16K
    6. 9385
    Prev
    Next
    INDEX
    Explanations

    verbs associated with transformation or change

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

    Followed by articles or adjectives after "become"

    np_acts-logits-general · gemini-2.0-flash

    state after becoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gawas
    -0.73
     Langue
    -0.60
     fortfarande
    -0.60
    still
    -0.60
    always
    -0.58
     Neutr
    -0.57
     sedang
    -0.57
     Already
    -0.57
     ftill
    -0.56
     chegando
    -0.55
    POSITIVE LOGITS
     increasingly
    0.89
    kannya
    0.78
     become
    0.74
     became
    0.73
     progressively
    0.70
     consultato
    0.67
     involved
    0.66
     acquainted
    0.65
     quite
    0.63
    Become
    0.63
    Activations Density 0.110%

    No Known Activations