© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 3313
    Prev
    Next
    INDEX
    Explanations

    instances of the word "come" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.76
    ValueStyle
    -0.73
    ſelf
    -0.73
    ftagPool
    -0.71
     Administrativna
    -0.71
     beſte
    -0.70
     verſ
    -0.69
    <unused41>
    -0.69
    <unused14>
    -0.68
    <unused28>
    -0.68
    POSITIVE LOGITS
     come
    3.48
     comes
    3.20
     came
    3.02
    come
    2.98
     Come
    2.91
    Come
    2.88
     COME
    2.84
    comes
    2.78
     Comes
    2.70
     coming
    2.67
    Activations Density 0.129%

    No Known Activations