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. 10-GEMMASCOPE-RES-16K
    6. 2937
    Prev
    Next
    INDEX
    Explanations

    references to dimensions in mathematical and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    AutoScale
    -0.99
    Atsauces
    -0.93
     HasFactory
    -0.89
    AndEndTag
    -0.86
     estekak
    -0.86
     NSCoder
    -0.85
     procédure
    -0.81
    addCriterion
    -0.81
     "..\..\
    -0.81
     resourceCulture
    -0.80
    POSITIVE LOGITS
     dimensions
    1.69
     Dimension
    1.65
     dimension
    1.62
    dimension
    1.58
    Dimension
    1.55
     Dimensions
    1.51
    dimensions
    1.47
     DIMENSION
    1.44
    Dimensions
    1.40
    dimen
    1.32
    Activations Density 0.085%

    No Known Activations