© 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. 9444
    Prev
    Next
    INDEX
    Explanations

    technical terms related to installation and configuration processes

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

    ending in "er," "or," or related suffixes

    np_acts-logits-general · gemini-2.0-flash

    estimation, sliders, execution, stepper

    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
     défendre
    -0.72
    الحياه
    -0.69
     prouver
    -0.68
     conclure
    -0.67
     prévoir
    -0.67
    HtmlAttribute
    -0.67
     peindre
    -0.66
    MemoryWarning
    -0.66
     convaincre
    -0.66
     décrire
    -0.65
    POSITIVE LOGITS
     Adder
    0.84
     adder
    0.82
     Walker
    0.82
     Maker
    0.80
     Weaver
    0.79
    eller
    0.79
     Eater
    0.79
     Ripper
    0.78
    ender
    0.78
    oner
    0.78
    Activations Density 0.689%

    No Known Activations