© 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. 6659
    Prev
    Next
    INDEX
    Explanations

    references to the term "Lan" and its variations in context

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

    starting with "Lan"

    np_acts-logits-general · gemini-2.0-flash

    Lan or Lam followed by specific suffixes

    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
    SourceChecksum
    -0.64
    EDEFAULT
    -0.63
    下载附件
    -0.61
     ***/
    -0.61
    OGND
    -0.60
    ffled
    -0.59
     لينك
    -0.59
    ModelAdmin
    -0.58
    JAMIN
    -0.58
    ]='\
    -0.56
    POSITIVE LOGITS
     lask
    0.56
     lanza
    0.53
     lancia
    0.51
    ExecuteReader
    0.49
     Lan
    0.46
    Lan
    0.44
    ौर
    0.44
     dives
    0.44
     IllegalArgument
    0.43
    imbawa
    0.43
    Activations Density 0.179%

    No Known Activations