© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11477
    Prev
    Next
    INDEX
    Explanations

    topics related to marine life and diving experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.72
    GOTREF
    -0.51
     henvisninger
    -0.47
     ***!
    -0.47
    jsxFileName
    -0.46
    interopRequire
    -0.46
     AttributeSet
    -0.43
    Хьажоргаш
    -0.40
    KommentareTeilen
    -0.40
    Šaltiniai
    -0.40
    POSITIVE LOGITS
     diving
    0.81
     dive
    0.75
     Diving
    0.74
     Dive
    0.74
    diving
    0.68
     snorkel
    0.68
    Diving
    0.68
     underwater
    0.66
     dives
    0.66
     diver
    0.66
    Activations Density 0.189%

    No Known Activations