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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2182
    Prev
    Next
    INDEX
    Explanations

    elements related to geographical locations and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.36
    RegressionTest
    -0.36
     향
    -0.36
    quisar
    -0.36
     place
    -0.34
     piłkarz
    -0.33
    범
    -0.32
    IRQn
    -0.32
     influence
    -0.31
    ↹
    -0.31
    POSITIVE LOGITS
    CloseOperation
    0.67
    CppMethod
    0.61
     nonUne
    0.57
    +#+
    0.56
    DispatchToProps
    0.55
    WebServlet
    0.50
    OGND
    0.50
     kohdetta
    0.49
    webElementXpaths
    0.49
    étoit
    0.49
    Activations Density 0.356%

    No Known Activations