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. 3347
    Prev
    Next
    INDEX
    Explanations

    references to variables and function parameters in programming contexts

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

    Code snippets: variable assignments and options

    np_acts-logits-general · gemini-2.0-flash

    assignment and updates

    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
     henvisninger
    -0.55
     (++
    -0.50
    vesen
    -0.48
    ₂+
    -0.48
    قایناقلار
    -0.47
    nodoc
    -0.47
    StackNavigator
    -0.45
    acherous
    -0.45
    PreferredItem
    -0.45
     Illuminate
    -0.45
    POSITIVE LOGITS
     =
    0.77
     &=
    0.70
     $=$
    0.69
    AccessorTable
    0.69
     =
    
    0.67
    ंदीखरीदारी
    0.66
     ویکی‌پدیا
    0.64
     }=\
    0.63
     iprot
    0.62
     Roskov
    0.61
    Activations Density 0.111%

    No Known Activations