Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2961
    Prev
    Next
    INDEX
    Explanations

    variations of punctuation, especially periods and colons

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

    Text following "A:" or question introductions

    np_acts-logits-general · gemini-2.0-flash

    o following "A:"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DrawerLayout
    -0.60
    inquirer
    -0.58
     <<<<<<<<<<<<<<
    -0.55
     autorytatywna
    -0.55
     xrange
    -0.54
    Vegeu
    -0.54
     ModelRenderer
    -0.53
    AndroidJUnit
    -0.53
    TextMessage
    -0.53
    DrawerToggle
    -0.53
    POSITIVE LOGITS
     @
    0.65
    NameInMap
    0.62
    InputTagHelper
    0.62
    Hello
    0.62
    Edit
    0.61
    edit
    0.60
     Hello
    0.59
     EDIT
    0.58
    >`;
    0.58
    LabelTagHelper
    0.57
    Activations Density 0.077%

    No Known Activations