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. 5667
    Prev
    Next
    INDEX
    Explanations

    closing braces and statement terminators in coding syntax

    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
    äle
    -0.50
     force
    -0.46
    rilis
    -0.43
     non
    -0.42
     reverse
    -0.42
     liner
    -0.42
     rép
    -0.41
     chúng
    -0.41
     timur
    -0.41
     failure
    -0.40
    POSITIVE LOGITS
    expandindo
    1.03
    GEBURTSDATUM
    0.79
    endmodule
    0.78
     disambiguazione
    0.72
     crutches
    0.71
     AssemblyVersion
    0.70
    verwijspagina
    0.70
    )\}
    0.69
    "]));
    0.68
     snippetHide
    0.66
    Activations Density 0.071%

    No Known Activations