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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16167
    Prev
    Next
    INDEX
    Explanations

    references to successful fundraising or promotional activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    DispatchToProps
    -0.69
    ंदीखरीदारी
    -0.68
     getItemId
    -0.62
     onBackPressed
    -0.60
    InstrumentedTest
    -0.59
     payé
    -0.58
    Espèce
    -0.56
    ondissement
    -0.56
    IsPostBack
    -0.55
     podjela
    -0.55
    POSITIVE LOGITS
     surpassed
    0.75
     exceeded
    0.72
     amass
    0.63
     amassed
    0.63
     succès
    0.62
     surpassing
    0.60
     success
    0.59
    Thousands
    0.59
     surpass
    0.59
     overwhelmingly
    0.59
    Activations Density 0.233%

    No Known Activations