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. 6625
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical examinations and analyses

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

    Follows a type of investigation or study

    np_acts-logits-general · gemini-2.0-flash

    analysis reveals research findings

    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
    istoitu
    -0.84
     оригіналу
    -0.65
    EDEFAULT
    -0.63
     createSprite
    -0.58
     AssemblyTitle
    -0.54
    LEncoder
    -0.54
     doInBackground
    -0.53
     protoimpl
    -0.51
    Zapraszamy
    -0.50
    ttin
    -0.50
    POSITIVE LOGITS
     shows
    1.94
     reveals
    1.85
     showed
    1.83
     show
    1.73
     reveal
    1.71
     revealed
    1.68
    shows
    1.66
     Shows
    1.62
     menunjukkan
    1.57
     showing
    1.56
    Activations Density 1.399%

    No Known Activations