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. 13-GEMMASCOPE-RES-16K
    6. 285
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms and results in experimental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statistical analysis references and p-values in scientific contexts.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trou
    -0.49
    risi
    -0.49
     Esp
    -0.46
     trouble
    -0.45
    top
    -0.44
    ris
    -0.44
    lov
    -0.43
     Intelligence
    -0.42
     Top
    -0.42
     top
    -0.42
    POSITIVE LOGITS
    UnitTesting
    0.92
    ItemBackground
    0.80
    QMetaType
    0.79
     propOrder
    0.77
    AnimationsModule
    0.77
     CreateTagHelper
    0.76
     Shakspeare
    0.75
    Демографія
    0.74
    TargetException
    0.71
    expandindo
    0.71
    Activations Density 0.968%

    No Known Activations