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. 7-GEMMASCOPE-RES-16K
    6. 6824
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to citizenship and immigration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Winkler
    -0.52
     ajudá
    -0.51
     Raccoon
    -0.49
    市镇
    -0.48
    Так
    -0.44
    شر
    -0.44
     gostar
    -0.43
     sphere
    -0.43
     vita
    -0.42
     fermés
    -0.42
    POSITIVE LOGITS
    \{\\
    0.78
    expandindo
    0.71
     AspNetCore
    0.66
    انيف
    0.62
    NewUrlParser
    0.62
     DbSet
    0.60
     дописавши
    0.60
    Filmografie
    0.59
    Према
    0.58
    Ligações
    0.57
    Activations Density 0.219%

    No Known Activations