© 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. 15185
    Prev
    Next
    INDEX
    Explanations

    references to programming package declarations

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

    Java package declarations

    np_acts-logits-general · gemini-2.0-flash

    package/com namespace

    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
    principalColumn
    -1.06
     itſelf
    -0.92
     tartalomajánló
    -0.83
    دانشنامهٔ
    -0.83
     المعيارى
    -0.83
    AntiForgeryToken
    -0.82
     ſever
    -0.80
     Efq
    -0.80
     purpoſe
    -0.79
    berdayakan
    -0.78
    POSITIVE LOGITS
     com
    1.14
     main
    0.68
     co
    0.55
     f
    0.53
     top
    0.53
     se
    0.52
     fin
    0.52
     Se
    0.51
     me
    0.51
     model
    0.50
    Activations Density 0.080%

    No Known Activations