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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 7008
    Prev
    Next
    INDEX
    Explanations

    terms related to testing or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ില
    -0.62
    PerformLayout
    -0.62
    ConfigureAwait
    -0.59
    InvalidProtocol
    -0.59
     master
    -0.55
     Staf
    -0.55
    дыду
    -0.54
    coup
    -0.54
    Corne
    -0.52
    gamon
    -0.52
    POSITIVE LOGITS
     testing
    2.91
     Testing
    2.84
    testing
    2.73
    Testing
    2.61
     TESTING
    2.48
    TESTING
    2.25
     tested
    1.78
     Tested
    1.57
    tested
    1.56
     tester
    1.44
    Activations Density 0.172%

    No Known Activations