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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6603
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the term "Victoria" and concepts related to memorable experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    visiae
    -0.63
    出版年
    -0.56
    MessageOf
    -0.56
    vene
    -0.55
     MonoBehaviour
    -0.53
    astify
    -0.52
    setVerticalGroup
    -0.51
    ReusableCell
    -0.50
     Mammal
    -0.49
    AnimationsModule
    -0.49
    POSITIVE LOGITS
     Euro
    0.79
    Euro
    0.70
     Victoria
    0.66
     Maria
    0.60
    Victoria
    0.60
     Anna
    0.59
    __':
    
    0.59
    Victor
    0.56
     Luke
    0.54
    __':
    0.54
    Activations Density 0.064%

    No Known Activations