© 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. 2899
    Prev
    Next
    INDEX
    Explanations

    categories and attributes related to films and media

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

    Follows a colon, often introducing a category/type

    np_acts-logits-general · gemini-2.0-flash

    list item category or type

    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
     too
    -0.42
     all
    -0.39
    Abstracts
    -0.36
     som
    -0.36
    -(-
    -0.35
    getHeader
    -0.34
    نامه
    -0.34
     among
    -0.34
     a
    -0.34
    select
    -0.34
    POSITIVE LOGITS
     Location
    1.04
    Location
    0.91
    GEBURTSDATUM
    0.90
     location
    0.87
     Type
    0.85
     Date
    0.82
     Status
    0.81
     Duration
    0.79
     Reſ
    0.78
    SBATCH
    0.77
    Activations Density 0.433%

    No Known Activations