Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 2028
    Prev
    Next
    INDEX
    Explanations

    negative statements or negations in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.77
    CodeAttribute
    -0.69
    InlineData
    -0.69
     aimable
    -0.68
     émotion
    -0.66
     topl
    -0.65
     ouverture
    -0.64
    spesies
    -0.64
     lush
    -0.64
     avoient
    -0.63
    POSITIVE LOGITS
    )$_
    1.05
    '")
    0.97
    '])
    
    0.94
    '):
    
    0.92
    '),
    
    0.91
    '))
    
    0.90
    ')"
    0.87
    '},
    
    0.86
    ')],
    0.86
    "]),
    0.85
    Activations Density 0.030%

    No Known Activations