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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11862
    Prev
    Next
    INDEX
    Explanations

    instances of the word "could" 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 @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewType
    -0.78
    soort
    -0.72
     FontWeight
    -0.71
     Sirs
    -0.68
     nawr
    -0.63
    談社
    -0.63
     chakras
    -0.62
    InvalidProtocol
    -0.60
     BOP
    -0.60
    __()
    -0.60
    POSITIVE LOGITS
     conceivably
    0.99
     potentially
    0.90
     possibly
    0.88
     theoretically
    0.86
     Possibly
    0.75
    potentially
    0.74
    possibly
    0.72
     COULD
    0.68
    entially
    0.65
     évent
    0.64
    Activations Density 0.086%

    No Known Activations