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. 3-GEMMASCOPE-RES-16K
    6. 11203
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight the importance of "the first thing" or significant initial actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppColors
    -0.71
     AspNetCore
    -0.70
     autorytatywna
    -0.68
    horabuena
    -0.68
    ///</
    -0.67
    NUMX
    -0.66
    
    -0.64
    ̈́
    -0.60
    Халык
    -0.60
    ">//
    -0.60
    POSITIVE LOGITS
    eleste
    0.61
    getSystemService
    0.51
    repr
    0.44
    »
    0.44
    Билгалдахарш
    0.43
    WithFormat
    0.42
     am
    0.42
    umentación
    0.42
    laar
    0.42
    Mockito
    0.42
    Activations Density 0.330%

    No Known Activations