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. 1-GEMMASCOPE-RES-16K
    6. 13537
    Prev
    Next
    INDEX
    Explanations

    negative expressions or phrases, particularly those related to situations of loss or disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.09
    aarrggbb
    -1.00
     nahilalakip
    -0.96
     Winaray
    -0.85
     Italijani
    -0.85
     Majefty
    -0.82
     auffi
    -0.80
    SourceChecksum
    -0.75
     joaat
    -0.74
     Monfieur
    -0.73
    POSITIVE LOGITS
     Out
    0.72
     out
    0.69
     OUT
    0.68
    Out
    0.62
    out
    0.54
     estekak
    0.53
    OUT
    0.52
     Auss
    0.48
      
    0.45
    utate
    0.44
    Activations Density 0.095%

    No Known Activations