© 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. 22-GEMMASCOPE-RES-16K
    11. 7059
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating informative communication and action

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

    Preceding words to "us"

    np_acts-logits-general · gemini-2.0-flash

    tell us or with us

    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
    our
    -0.74
     ourselves
    -0.74
     Our
    -0.70
    apunov
    -0.67
    Our
    -0.66
    myself
    -0.65
    OUR
    -0.65
     nossos
    -0.64
     our
    -0.63
     him
    -0.62
    POSITIVE LOGITS
     us
    2.62
    us
    1.57
     Us
    1.53
    Us
    1.41
     нас
    1.21
     нам
    0.97
     nás
    0.96
     usa
    0.93
    US
    0.93
     US
    0.91
    Activations Density 0.243%

    No Known Activations