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. 5-GEMMASCOPE-RES-16K
    6. 3730
    Prev
    Next
    INDEX
    Explanations

    references to specific items, particularly food and sports related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CGRect
    -0.56
    不起
    -0.52
    quelize
    -0.45
     adults
    -0.45
     sztuki
    -0.44
     wystar
    -0.44
     szól
    -0.44
     nhàng
    -0.44
    εια
    -0.43
     quietly
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.91
     kaarangay
    0.88
    tagHelperRunner
    0.87
    GEBURTSDATUM
    0.83
    writeField
    0.78
    XmlIgnore
    0.77
     виправивши
    0.76
     '\\;'
    0.74
    IsContent
    0.72
     تضيفلها
    0.72
    Activations Density 1.288%

    No Known Activations