Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8725
    Prev
    Next
    INDEX
    Explanations

    references to poetic or literary works and expressions of emotional moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
     competition
    -0.37
     DeV
    -0.35
    multicolumn
    -0.35
    ificados
    -0.33
     pleaſure
    -0.33
     verste
    -0.33
     extensive
    -0.33
    nande
    -0.32
     Sosial
    -0.32
     fiscal
    -0.32
    POSITIVE LOGITS
     CreateTagHelper
    0.62
    LookAnd
    0.59
     okuyayım
    0.56
     ujednoznacz
    0.55
    NameInMap
    0.54
    Personendaten
    0.51
    peteer
    0.51
    ➯
    0.51
    blurRadius
    0.49
    sizeCache
    0.49
    Activations Density 0.723%

    No Known Activations