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. 21-GEMMASCOPE-RES-16K
    6. 608
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijani
    -0.55
    webElementXpaths
    -0.47
    すすめ
    -0.47
    য়ে
    -0.46
    awtextra
    -0.44
    CopyWith
    -0.43
    共和国
    -0.42
    AddressBook
    -0.41
    charest
    -0.41
    errHandler
    -0.40
    POSITIVE LOGITS
    >{@
    0.67
    الحياه
    0.67
    specifier
    0.64
    تفصیلات
    0.64
    argument
    0.61
    tableFuture
    0.61
     Eſ
    0.60
    ))))))))
    0.60
    TokenNameLPAREN
    0.58
    ApiModelProperty
    0.58
    Activations Density 0.044%

    No Known Activations