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. 13908
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'Y' used in various contexts

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

    Followed by "ng" or other uncommon two-letter sequences

    np_acts-logits-general · gemini-2.0-flash

    Y followed by ng

    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
     AssemblyProduct
    -0.64
     مباشرة
    -0.54
    iena
    -0.52
     defStyle
    -0.48
     direct
    -0.47
     directly
    -0.47
     direto
    -0.46
    directly
    -0.44
     Direkt
    -0.44
     bort
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.86
     eventdata
    0.66
    mybatisplus
    0.59
    DeleteBehavior
    0.59
    ModelAdmin
    0.55
    Tembelea
    0.54
    MLLoader
    0.53
     NUKAT
    0.53
     hypothalamus
    0.53
    principalColumn
    0.53
    Activations Density 0.135%

    No Known Activations