© 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. 7-GEMMASCOPE-RES-16K
    11. 6709
    Prev
    Next
    INDEX
    Explanations

    transitions or sequences of events in a narrative

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

    time-related phrases indicating sequential actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kidding
    -0.68
    RectangleBorder
    -0.68
     somethin
    -0.67
    nobody
    -0.66
    ostante
    -0.65
     stinks
    -0.63
    ftagPool
    -0.62
     everybody
    -0.61
     Everybody
    -0.60
    ReusableCell
    -0.60
    POSITIVE LOGITS
     proceeded
    0.79
    tvguidetime
    0.69
     vervolgens
    0.67
     thereafter
    0.64
     proceed
    0.63
     further
    0.62
     subsequently
    0.62
     embarked
    0.62
    وأضاف
    0.61
    Diweddarwch
    0.60
    Activations Density 0.175%

    No Known Activations