© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11260
    Prev
    Next
    INDEX
    Explanations

    patterns related to template bindings and structural elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.96
    AndEndTag
    -0.89
    省市镇
    -0.88
     InputDecoration
    -0.84
    Попис
    -0.84
     jsPsych
    -0.81
     CreateTagHelper
    -0.80
    TagHelpers
    -0.76
    AddHtmlAttribute
    -0.76
     Roskov
    -0.75
    POSITIVE LOGITS
    ="{{
    0.87
     Lett
    0.60
     JButton
    0.59
    Lett
    0.58
    JButton
    0.55
    )))));
    0.54
    جان
    0.48
     lett
    0.48
     Mont
    0.47
     vit
    0.47
    Activations Density 0.034%

    No Known Activations