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. 11-GEMMASCOPE-RES-16K
    6. 2043
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to ingredients in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.82
     insuffisamment
    -0.78
    expandindo
    -0.78
    InjectAttribute
    -0.78
    مصادر
    -0.77
     الاطلاع
    -0.76
    CrossRef
    -0.75
    StoreMessageInfo
    -0.74
     BoxDecoration
    -0.72
     BorderSide
    -0.72
    POSITIVE LOGITS
     الذات
    0.52
     each
    0.51
     graduated
    0.49
    СТВА
    0.47
    IMATE
    0.46
    ütter
    0.46
    EXTERN
    0.44
    おきます
    0.44
    łbym
    0.43
    idar
    0.43
    Activations Density 0.210%

    No Known Activations