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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10201
    Prev
    Next
    INDEX
    Explanations

    statistical measurements and analyses in experimental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.71
     Лег
    -0.61
     Parke
    -0.58
     alien
    -0.56
    ihnach
    -0.51
     AssemblyProduct
    -0.49
     Tomlinson
    -0.49
    arraycopy
    -0.49
    TypedDataSet
    -0.48
    XmlAccessType
    -0.48
    POSITIVE LOGITS
     uncertainty
    1.18
     standard
    1.17
     error
    1.15
     variance
    1.13
     errors
    1.08
     uncertainties
    1.06
     Standard
    1.05
    standard
    1.03
     Uncertainty
    1.02
    uncertainty
    1.01
    Activations Density 1.660%

    No Known Activations