© 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 - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2731
    Prev
    Next
    INDEX
    Explanations

    instances of the word "delete" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #![
    -0.76
     initComponents
    -0.65
     invokingState
    -0.65
    il
    -0.59
     تعرض
    -0.57
    dil
    -0.56
     kits
    -0.56
    MsgBox
    -0.56
    ToBounds
    -0.55
     setOpen
    -0.54
    POSITIVE LOGITS
    
    1.01
    ftagPool
    0.90
     Nazare
    0.87
     SND
    0.72
    ğlık
    0.71
    \}}
    0.70
     Clube
    0.70
    hbase
    0.68
     atve
    0.68
    malink
    0.68
    Activations Density 0.336%

    No Known Activations