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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-65K
    6. 53471
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns in various languages

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

    demonstrative adjectives (this/that)

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Ursache
    -0.61
     детстве
    -0.58
     Rul
    -0.58
     Bestimmungen
    -0.54
    ragamo
    -0.53
     cazul
    -0.50
    umerate
    -0.50
     sedation
    -0.49
     Kindern
    -0.48
    ódz
    -0.48
    POSITIVE LOGITS
     continúas
    0.89
    Enllaces
    0.88
     deste
    0.87
     particular
    0.84
    Dieses
    0.81
    Este
    0.80
     Neste
    0.79
    Nesta
    0.79
    Đây
    0.79
     este
    0.78
    Activations Density 0.003%

    No Known Activations