Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 5975
    Prev
    Next
    INDEX
    Explanations

    the conjunction "or" in various contexts

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

    preceding "or"

    np_acts-logits-general · gemini-2.0-flash

    connects alternatives or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.70
     createState
    -0.65
    thâu
    -0.65
    TagMode
    -0.63
    AddressBook
    -0.61
     Majefty
    -0.61
     itſelf
    -0.61
     fubject
    -0.61
    Geplaatst
    -0.59
     Anſ
    -0.56
    POSITIVE LOGITS
     else
    1.64
     even
    1.42
     alternatively
    1.27
     perhaps
    1.22
     simply
    1.21
     otherwise
    1.21
    ginal
    1.11
     maybe
    1.11
    ients
    1.10
    else
    1.09
    Activations Density 0.300%

    No Known Activations