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. 51
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that highlight advantages or differences between methods or entities

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

    comparative phrases highlighting differences or advantages, often using "unlike" or comparisons with "other".

    oai_token-act-pair · gpt-4oTriggered by @timna
    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
    toHaveBeen
    -0.43
     Transporter
    -0.40
    neman
    -0.40
    ışık
    -0.39
     Suc
    -0.39
    ();)
    -0.38
    Suara
    -0.37
    Supp
    -0.37
     transporter
    -0.36
    instant
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.87
    Portail
    0.80
     समीक्षक
    0.79
    énéral
    0.77
     BoxDecoration
    0.73
    MigrationBuilder
    0.70
    StoryboardSegue
    0.67
    TintMode
    0.67
    Према
    0.66
    webElement
    0.65
    Activations Density 0.293%

    No Known Activations