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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8569
    Prev
    Next
    INDEX
    Explanations

    proper names and entities related to businesses, locations, or legal cases

    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
    BufferException
    -0.40
    XOXO
    -0.39
    fully
    -0.39
    ug
    -0.39
    sterdam
    -0.38
    rodalom
    -0.38
    Nasty
    -0.38
    CELONA
    -0.37
     infatu
    -0.37
    WSER
    -0.37
    POSITIVE LOGITS
    }{*}{
    0.58
    GroupLayout
    0.56
    AnchorStyles
    0.53
     viewDidLoad
    0.53
    Portale
    0.52
     समीक्षाओं
    0.52
     kaynağından
    0.51
    MarshalTo
    0.50
     Paragon
    0.49
     informée
    0.48
    Activations Density 1.114%

    No Known Activations