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 - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14828
    Prev
    Next
    INDEX
    Explanations

    references to ancient civilizations and cultures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelAndView
    -0.62
    teness
    -0.59
    mixture
    -0.57
     Threads
    -0.57
    neros
    -0.54
    Personendaten
    -0.54
    '}';
    -0.54
    っこう
    -0.53
     Friar
    -0.53
    RATIO
    -0.53
    POSITIVE LOGITS
     ancient
    1.20
     Ancient
    1.16
    Ancient
    1.06
    ancient
    1.02
     ANCI
    0.95
     ancients
    0.81
    ANCI
    0.76
     древ
    0.68
    antiate
    0.66
     Anci
    0.66
    Activations Density 0.053%

    No Known Activations