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. 5-GEMMASCOPE-RES-16K
    6. 11732
    Prev
    Next
    INDEX
    Explanations

    the presence of brackets or related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -1.05
    
    -0.96
    AndEndTag
    -0.93
     varandra
    -0.91
    featureID
    -0.89
    })`
    -0.89
    MessageOf
    -0.88
    ']))
    
    -0.88
     $_"
    -0.88
     ExecuteAsync
    -0.87
    POSITIVE LOGITS
     [
    1.38
    [
    1.00
     (
    0.99
    【
    0.78
     [[
    0.78
    #[
    0.76
    {[
    0.73
    {(
    0.72
    ![
    0.70
    vid
    0.66
    Activations Density 0.471%

    No Known Activations