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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113934
    Prev
    Next
    INDEX
    Explanations

    references to contemporary art and culture

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

    contemporary fields and practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inscrivez
    -0.59
     chré
    -0.54
     feroit
    -0.52
     ainfi
    -0.51
     Keuangan
    -0.50
     peines
    -0.49
     étr
    -0.49
     Connectez
    -0.48
     gouver
    -0.47
     rempliss
    -0.47
    POSITIVE LOGITS
     contemporary
    1.07
    contemporary
    0.97
     Contemporary
    0.85
     contempor
    0.84
    Contemporary
    0.83
     contemporaneous
    0.80
     CONTEM
    0.79
     contemporánea
    0.68
     contemp
    0.66
     Contempor
    0.66
    Activations Density 0.008%

    No Known Activations