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. 12-GEMMASCOPE-RES-16K
    6. 2975
    Prev
    Next
    INDEX
    Explanations

    references to package names in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.03
    IsContent
    -1.03
    RenderAtEndOf
    -0.90
     Administrativna
    -0.89
    WithIOException
    -0.87
    OGND
    -0.83
    #
    -0.82
     noqa
    -0.81
     pinulongan
    -0.80
     disambiguazione
    -0.80
    POSITIVE LOGITS
     com
    0.95
     Com
    0.68
    Com
    0.64
    com
    0.56
     www
    0.53
    الدراسه
    0.49
     például
    0.49
    깥
    0.47
     A
    0.45
     W
    0.44
    Activations Density 0.057%

    No Known Activations