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. 3-GEMMASCOPE-RES-16K
    6. 10026
    Prev
    Next
    INDEX
    Explanations

    references to culture and cultural themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ReactDOM
    -0.77
    __':
    -0.66
    valbard
    -0.66
     oeufs
    -0.66
    Sidenav
    -0.65
     FontWeight
    -0.64
     pianoforte
    -0.64
    ไม้
    -0.64
    ConstraintMaker
    -0.61
    Glej
    -0.60
    POSITIVE LOGITS
     culture
    3.29
     Culture
    3.05
    culture
    2.98
    Culture
    2.92
     CULTURE
    2.76
     cultures
    2.75
    CULTURE
    2.68
     Cultures
    2.36
     cultura
    2.35
    cultures
    2.25
    Activations Density 0.048%

    No Known Activations