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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 923
    Prev
    Next
    INDEX
    Explanations

    instances of disbelief or skepticism in narratives

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

    expressions of personal belief or conviction

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

    location-related words

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     وتسجيلات
    -0.65
    enumii
    -0.60
    över
    -0.54
     فريبيس
    -0.54
    ISupport
    -0.50
     TestBed
    -0.49
    SqlSession
    -0.49
    发表于
    -0.48
    Portály
    -0.47
     ench
    -0.47
    POSITIVE LOGITS
     here
    2.64
     Here
    2.12
    here
    2.09
    Here
    2.01
     aquí
    1.97
     HERE
    1.77
     aqui
    1.64
     здесь
    1.63
    HERE
    1.62
     ici
    1.61
    Activations Density 0.090%

    No Known Activations