© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8578
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and duration

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

    "to come"

    np_acts-logits-general · gemini-2.0-flash

    future continuation

    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
    PDOException
    -0.64
    PerformLayout
    -0.58
     LoggerFactory
    -0.56
    Tikang
    -0.55
     myſelf
    -0.54
    )\}
    -0.54
    findpost
    -0.53
    OPSIS
    -0.49
     Majefty
    -0.48
     itſelf
    -0.48
    POSITIVE LOGITS
     come
    3.54
     comes
    3.25
     coming
    3.08
     came
    3.03
    come
    2.94
     Come
    2.93
     COME
    2.89
    Come
    2.86
    comes
    2.80
     Comes
    2.80
    Activations Density 0.617%

    No Known Activations