© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8865
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "do" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.75
     ComVisible
    -0.62
    yntaxException
    -0.60
    marshaller
    -0.58
     Lleva
    -0.58
    cnica
    -0.57
     @"/
    -0.57
    ագրություններ
    -0.57
    balah
    -0.56
    Composable
    -0.56
    POSITIVE LOGITS
    раздо
    0.66
     does
    0.65
    躇
    0.62
     DOES
    0.60
     Clarendon
    0.58
     doesn
    0.57
     writ
    0.55
    does
    0.54
    urahan
    0.54
    มิ
    0.52
    Activations Density 0.262%

    No Known Activations