© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11219
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming functions, database operations, and redirects in web development

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

    Code snippets with functions/variables

    np_acts-logits-general · gemini-2.0-flash

    function definitions and calls

    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
    توض
    -0.50
    kuper
    -0.50
    onzo
    -0.49
    herence
    -0.49
    presenter
    -0.48
     Política
    -0.47
     politica
    -0.47
     modeled
    -0.46
    Technic
    -0.46
     dataSet
    -0.45
    POSITIVE LOGITS
    ()
    1.40
    (),
    0.98
    ().
    0.95
    ()
    
    0.93
    ())
    0.87
    ():
    0.86
     ()
    0.86
    //
    0.85
    >>()
    0.85
    ()->
    0.83
    Activations Density 0.154%

    No Known Activations