© 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. 9488
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a list or examples

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

    Followed by a number or a measurement

    np_acts-logits-general · gemini-2.0-flash

    just examples sampling listing

    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
     gynhyrchwyd
    -0.68
     ModelExpression
    -0.61
    MigrationBuilder
    -0.52
     sitten
    -0.51
     smtplib
    -0.51
    prüche
    -0.51
    WebElementEntity
    -0.47
     useRouter
    -0.47
    таратура
    -0.47
    PYX
    -0.45
    POSITIVE LOGITS
     just
    1.11
     sampling
    1.03
     among
    1.03
     sample
    0.96
    just
    0.93
    sampling
    0.91
     parmi
    0.91
     examples
    0.89
    among
    0.89
    只是
    0.88
    Activations Density 0.141%

    No Known Activations