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. 15-GEMMASCOPE-RES-16K
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    phrases related to democracy and participation in governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    celled
    -0.59
    otsu
    -0.56
    LEGGI
    -0.56
    }}]{
    -0.55
    ftance
    -0.53
     PLWABN
    -0.53
    cheinend
    -0.53
    messageInfo
    -0.52
     vinto
    -0.52
    Notae
    -0.52
    POSITIVE LOGITS
     hence
    1.41
    hence
    1.21
     Hence
    1.21
     therefore
    1.19
    Hence
    1.14
     поэтому
    1.12
     daarom
    1.07
     därför
    1.06
     Derfor
    1.06
     Deshalb
    1.02
    Activations Density 0.386%

    No Known Activations