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. 10-GEMMASCOPE-RES-16K
    6. 10861
    Prev
    Next
    INDEX
    Explanations

    structured instances of evaluation and reporting within scientific or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tomorrow
    -0.73
    attuale
    -0.66
     attualmente
    -0.66
     ngayon
    -0.65
     derzeit
    -0.65
     künftig
    -0.64
     actuelles
    -0.63
    currently
    -0.63
     amanhã
    -0.61
    tomorrow
    -0.60
    POSITIVE LOGITS
     wasn
    1.00
     was
    0.99
     didn
    0.98
     did
    0.95
    Wasn
    0.94
     damals
    0.93
     Wasn
    0.92
     originally
    0.88
     went
    0.86
     weren
    0.86
    Activations Density 3.776%

    No Known Activations