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. 13-GEMMASCOPE-RES-16K
    6. 10055
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex biological processes and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdc
    -0.56
     päivä
    -0.51
     virginity
    -0.51
     Barnabas
    -0.48
     Edison
    -0.48
     Unable
    -0.46
    droje
    -0.46
     cytok
    -0.46
    věr
    -0.45
     Dawes
    -0.45
    POSITIVE LOGITS
     involves
    0.86
    volves
    0.83
     CreateTagHelper
    0.83
     a
    0.82
     involve
    0.77
     autorytatywna
    0.76
    uhkan
    0.75
     consist
    0.75
     comprises
    0.74
     either
    0.74
    Activations Density 0.552%

    No Known Activations