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. 16-GEMMASCOPE-RES-16K
    6. 12033
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

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

    Text after names or locations

    np_acts-logits-general · gemini-2.0-flash

    parts of names and places

    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
     المعيارى
    -1.24
     autorytatywna
    -1.16
    Autoritní
    -1.08
    GEBURTSDATUM
    -1.05
    NUMX
    -0.95
     nakalista
    -0.94
    RectangleBorder
    -0.93
     وتسجيلات
    -0.91
     الحره
    -0.90
    بوابة
    -0.87
    POSITIVE LOGITS
    ,
    0.83
    _
    0.44
    ta
    0.44
    j
    0.41
    let
    0.40
    tak
    0.39
     William
    0.39
    be
    0.39
    design
    0.39
    Name
    0.39
    Activations Density 0.227%

    No Known Activations