© 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. 7657
    Prev
    Next
    INDEX
    Explanations

    references to maximum and minimum values in various contexts

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

    maximum or minimum amounts

    np_acts-logits-general · gemini-2.0-flash

    minimum/maximum limits

    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
     AssemblyCompany
    -0.91
    IndentedString
    -0.69
    awtextra
    -0.63
     فريبيس
    -0.57
    [@"
    -0.55
    Билгалдахарш
    -0.54
     defStyle
    -0.54
     BeautifulSoup
    -0.54
    :"-"`
    -0.53
     {?>
    -0.53
    POSITIVE LOGITS
     amount
    0.86
     allowable
    0.81
     aantal
    0.73
    mium
    0.72
     achievable
    0.72
     number
    0.69
    ALLOWED
    0.68
     allowed
    0.68
     possible
    0.68
     mož
    0.68
    Activations Density 0.119%

    No Known Activations