© 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. 9706
    Prev
    Next
    INDEX
    Explanations

    technical or procedural language related to system operations and status updates

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

    Preceding "a" or "the"

    np_acts-logits-general · gemini-2.0-flash

    qualifiers or conditions

    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
     Roskov
    -0.67
    Them
    -0.65
    SuppressLint
    -0.64
    tamanya
    -0.61
    saraba
    -0.61
    Havolalar
    -0.60
    :].
    -0.57
     montón
    -0.57
    ViewFeatures
    -0.56
    scalatest
    -0.56
    POSITIVE LOGITS
     additional
    1.15
     sufficient
    1.10
     considerable
    1.04
    additional
    0.98
     significant
    0.97
     adequate
    0.97
     substantial
    0.95
     extensive
    0.94
     efforts
    0.90
     an
    0.86
    Activations Density 1.148%

    No Known Activations