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. 20-GEMMASCOPE-RES-16K
    6. 4321
    Prev
    Next
    INDEX
    Explanations

    references to institutional or regulatory challenges and processes

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

    Followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    by or through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     astore
    -0.62
    
    
    -0.53
    Diweddarwch
    -0.52
    ERÍA
    -0.51
    erapeutic
    -0.50
    XmlAccessorType
    -0.49
    WhereInput
    -0.48
    onViewCreated
    -0.47
    GeneratedMessage
    -0.47
    #
    -0.47
    POSITIVE LOGITS
     путем
    1.58
     by
    1.55
     poprzez
    1.38
     pamamagitan
    1.35
     mediante
    1.32
     indem
    1.28
     bằng
    1.24
     via
    1.19
     шля
    1.16
     using
    1.14
    Activations Density 1.783%

    No Known Activations