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. 13-GEMMASCOPE-RES-16K
    6. 4125
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" in various contexts and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.75
     ALR
    -0.71
    存于互联网档案馆
    -0.69
     xk
    -0.69
     shutil
    -0.68
     MotionEvent
    -0.68
     Monfieur
    -0.67
     bezeichneter
    -0.67
     Audiodateien
    -0.66
    anneer
    -0.66
    POSITIVE LOGITS
    webElementXpaths
    0.60
     to
    0.58
     صوتيه
    0.54
     or
    0.50
     such
    0.50
     at
    0.50
     in
    0.49
     direct
    0.48
    的情况下
    0.48
     with
    0.48
    Activations Density 0.154%

    No Known Activations