© 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. 9379
    Prev
    Next
    INDEX
    Explanations

    items that indicate significant changes or measures

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

    Follows a comma

    np_acts-logits-general · gemini-2.0-flash

    descriptive adjective phrases

    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
    Especially
    -0.60
     Especially
    -0.56
     &
    -0.47
     etc
    -0.46
     особенно
    -0.46
    RESUMO
    -0.45
     especially
    -0.45
    than
    -0.43
    standes
    -0.42
     خصوص
    -0.42
    POSITIVE LOGITS
     designed
    1.25
     consisting
    1.04
     capable
    1.02
     featuring
    0.98
     reminiscent
    0.95
    designed
    0.95
     whoſe
    0.94
     composed
    0.92
     resembling
    0.90
     aimed
    0.90
    Activations Density 0.479%

    No Known Activations