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. 18-GEMMASCOPE-RES-16K
    6. 1428
    Prev
    Next
    INDEX
    Explanations

    actions and processes that occur sequentially or in increments

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

    Text containing "one" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    one by one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.63
     >=",
    -0.63
    Trama
    -0.51
    IQR
    -0.50
    WithIOException
    -0.49
     geldig
    -0.47
     eternal
    -0.44
    Artículo
    -0.44
    Hentet
    -0.43
    ölcs
    -0.43
    POSITIVE LOGITS
     gradually
    2.17
     slowly
    2.06
     Gradually
    1.95
    slowly
    1.88
     Slowly
    1.81
     gradual
    1.81
    Slowly
    1.80
     progressively
    1.62
     постепенно
    1.62
     gradualmente
    1.58
    Activations Density 0.626%

    No Known Activations