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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12039
    Prev
    Next
    INDEX
    Explanations

    references to catalogs and cataloging processes

    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
    IUrlHelper
    -0.85
    ]}"
    -0.76
    ))->
    -0.75
     coton
    -0.72
    ValueStyle
    -0.69
     Afin
    -0.68
     WSU
    -0.68
    $_['
    -0.68
     Oilers
    -0.68
     Martine
    -0.67
    POSITIVE LOGITS
     catalog
    1.20
     Catalog
    1.14
     catalogo
    1.12
    catalog
    1.11
    Catalog
    1.09
     catalogue
    1.07
     catalogs
    1.03
     Catalogue
    0.96
     CATALOG
    0.95
     Jam
    0.95
    Activations Density 0.107%

    No Known Activations