© 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. 12414
    Prev
    Next
    INDEX
    Explanations

    terms related to financial metrics and modeling

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

    Preceding the word "when"

    np_acts-logits-general · gemini-2.0-flash

    when

    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
    قایناقلار
    -0.60
     jScrollPane
    -0.53
    <?
    -0.52
    ThroughAttribute
    -0.52
    //
    -0.51
    ьаж
    -0.49
    月号
    -0.49
    HasAnnotation
    -0.48
     surla
    -0.48
    Autoritní
    -0.48
    POSITIVE LOGITS
     when
    4.05
    when
    3.33
     quando
    3.03
     cuando
    2.98
     WHEN
    2.69
     когда
    2.67
    When
    2.62
     When
    2.58
     lorsque
    2.56
     lorsqu
    2.48
    Activations Density 3.040%

    No Known Activations