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. 10882
    Prev
    Next
    INDEX
    Explanations

    variations of the word "abstain" and its derivatives

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

    starting with "Ab" or "Abs"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Ab or Abs

    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
     nakalista
    -0.65
     Италијани
    -0.64
    isContained
    -0.61
    شهاد
    -0.61
    FailureListener
    -0.61
    ributions
    -0.59
     vVar
    -0.57
     yii
    -0.56
     >=",
    -0.56
    Migrations
    -0.56
    POSITIVE LOGITS
     Abs
    0.67
     AB
    0.61
     Abby
    0.59
     Ab
    0.59
     pathname
    0.58
     Zab
    0.56
     ABS
    0.55
    olute
    0.55
    CBN
    0.54
     ab
    0.53
    Activations Density 0.149%

    No Known Activations