© 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. 8630
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant locations or structures

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

    following "also," "which," "that," "can," or "since."

    np_acts-logits-general · gemini-2.0-flash

    hosting places or entities

    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
     doInBackground
    -0.66
     Arrive
    -0.61
     arrives
    -0.60
    WebVitals
    -0.59
    igshid
    -0.58
    ConstraintMaker
    -0.58
     kommet
    -0.57
    وعة
    -0.57
    OrWhiteSpace
    -0.56
    wiſe
    -0.56
    POSITIVE LOGITS
     hosting
    1.70
     hosts
    1.66
     host
    1.66
     hosted
    1.37
     Hosting
    1.33
    host
    1.31
    hosting
    1.28
    Hosting
    1.27
     Hosts
    1.22
     Host
    1.18
    Activations Density 0.388%

    No Known Activations