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. 14-GEMMASCOPE-RES-16K
    6. 13028
    Prev
    Next
    INDEX
    Explanations

    topics related to psychological and sociological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paroi
    -0.71
     couronne
    -0.67
    istoitu
    -0.62
    ympto
    -0.61
    cipar
    -0.60
     CORON
    -0.60
    𝘅
    -0.59
    profen
    -0.58
    bonds
    -0.58
     cơn
    -0.57
    POSITIVE LOGITS
    Demografie
    0.85
     pinulongan
    0.83
    ',)
    0.77
    Bibliographie
    0.76
    orology
    0.76
     technics
    0.76
    mography
    0.75
    iology
    0.74
    iography
    0.73
    Sinopse
    0.73
    Activations Density 0.487%

    No Known Activations