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. 4571
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "nil."

    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
    டைய
    -0.53
    mphony
    -0.50
     '/
    -0.48
     Norwe
    -0.48
     $('<
    -0.46
     sumpay
    -0.46
     feast
    -0.45
    HtmlAttribute
    -0.45
     dynamic
    -0.45
     Sardin
    -0.45
    POSITIVE LOGITS
     nil
    1.49
    nil
    1.08
     Nil
    1.00
    Nil
    0.98
    didSet
    0.86
     NIL
    0.84
    yntaxException
    0.78
    NotNil
    0.75
    ValueGenerated
    0.75
     CURLOPT
    0.75
    Activations Density 0.020%

    No Known Activations