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. 6121
    Prev
    Next
    INDEX
    Explanations

    references to large quantities and financial figures

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

    Plural forms of numbers

    np_acts-logits-general · gemini-2.0-flash

    large quantities and durations

    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
     
    -0.66
     @
    -0.66
     F
    -0.61
     (
    -0.60
    @
    -0.59
     plus
    -0.56
     four
    -0.55
     Par
    -0.52
     *
    -0.52
    :
    -0.52
    POSITIVE LOGITS
    ousands
    1.34
     Hundreds
    1.27
    hundreds
    1.25
    thousands
    1.23
     myſelf
    1.23
    Hundreds
    1.22
    Thousands
    1.20
     Thousands
    1.20
     itſelf
    1.18
     dizaines
    1.16
    Activations Density 0.196%

    No Known Activations