© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 28422
    Prev
    Next
    INDEX
    Explanations

    details related to film reviews, guidelines, and ethical considerations

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

    likewise, similarly, also

    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
    IsMutable
    -0.68
    ViewFeatures
    -0.64
    ="@+
    -0.58
    awtextra
    -0.56
    issements
    -0.52
    )=>{
    
    -0.50
    Personensuche
    -0.48
    Jîn
    -0.48
    ppas
    -0.48
    gnore
    -0.48
    POSITIVE LOGITS
     likewise
    2.06
     similarly
    1.87
     ebenfalls
    1.77
     meanwhile
    1.70
     also
    1.69
     тоже
    1.62
    Similarly
    1.62
    Likewise
    1.60
     Similarly
    1.58
     също
    1.56
    Activations Density 0.861%

    No Known Activations