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. 9-GEMMASCOPE-RES-16K
    6. 15293
    Prev
    Next
    INDEX
    Explanations

    components related to sports equipment and their mechanical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wise
    -0.49
    堆
    -0.47
    まと
    -0.47
    ыгана
    -0.46
    Портал
    -0.44
     acces
    -0.42
     Toujours
    -0.42
    Wise
    -0.42
    <bos>
    -0.41
    choice
    -0.41
    POSITIVE LOGITS
    zzleHttp
    0.77
    andExpect
    0.74
     ContentValues
    0.72
    ConstraintMaker
    0.69
    jsdelivr
    0.68
    setupUi
    0.67
    tagHelperRunner
    0.67
    GOTREF
    0.64
    ViewImports
    0.62
    AccessorTable
    0.60
    Activations Density 0.445%

    No Known Activations