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. 749
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to legal compliance and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     MainAxisSize
    -0.68
    LookAnd
    -0.68
    styleType
    -0.61
    ıntı
    -0.58
    memoized
    -0.56
    してみる
    -0.55
     protoimpl
    -0.54
    MigrationBuilder
    -0.53
    StackNavigator
    -0.53
    ьаж
    -0.52
    POSITIVE LOGITS
     otherwise
    3.51
     Otherwise
    3.48
    Otherwise
    3.47
    otherwise
    3.22
     altrimenti
    2.92
     OTHERWISE
    2.88
     else
    2.88
    否则
    2.53
     Else
    2.49
     ellers
    2.40
    Activations Density 0.476%

    No Known Activations