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. 16-GEMMASCOPE-RES-16K
    6. 6579
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements related to layout and styling conventions

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

    HTML class or id attributes

    np_acts-logits-general · gemini-2.0-flash

    SMR followed by structural elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.94
    Geplaatst
    -0.91
     propOrder
    -0.85
     Paglinawan
    -0.78
    expandindo
    -0.76
     présidenti
    -0.76
     Roskov
    -0.74
    
    -0.74
    windowFixed
    -0.73
     <<<<<<<<<<<<<<
    -0.72
    POSITIVE LOGITS
    div
    0.60
    row
    0.54
    dip
    0.53
     div
    0.52
    Div
    0.51
     central
    0.51
     Div
    0.50
    DPS
    0.50
    σταση
    0.49
    mbu
    0.49
    Activations Density 0.016%

    No Known Activations