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. 5-GEMMASCOPE-RES-16K
    6. 12106
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to starting or concluding events and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.68
    DidChange
    -0.58
     Màu
    -0.58
    CodeGen
    -0.58
    removeChild
    -0.58
    uities
    -0.58
     geldig
    -0.57
    TableAdapter
    -0.57
    isHidden
    -0.57
    atomy
    -0.57
    POSITIVE LOGITS
    BeginContext
    0.55
    parsedMessage
    0.49
    SharedCtor
    0.46
    UnknownFields
    0.46
     conclude
    0.45
     Begin
    0.45
    ),
    
    0.44
     ExecuteAsync
    0.44
    /*
    0.44
    IMPORTED
    0.43
    Activations Density 0.166%

    No Known Activations