Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12974
    Prev
    Next
    INDEX
    Explanations

    the name "Ay" or variations of the name "Aylan" in various contexts

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

    "Ay" followed by a specific letter

    np_acts-logits-general · gemini-2.0-flash

    Ayl, Aylo, Ayra

    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
     betweenstory
    -0.56
    createServer
    -0.56
    تمبر
    -0.54
    PointerException
    -0.52
    IsMutable
    -0.51
    rmtree
    -0.48
    DropTable
    -0.47
    \""
    -0.47
     ++)
    -0.47
     ever
    -0.46
    POSITIVE LOGITS
     ActionBar
    0.63
    oredCriteria
    0.61
    Datuak
    0.59
     utafitiHapana
    0.59
     Мексичка
    0.57
     <=",
    0.54
     Elapsed
    0.54
     Adsorption
    0.53
    Obrázky
    0.52
     Ay
    0.52
    Activations Density 0.098%

    No Known Activations