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. 158
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and event listeners in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming interface terms and listener-related code elements.

    oai_token-act-pair · gpt-4oTriggered by @timna
    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
     raiſ
    -0.79
     cauſe
    -0.76
     referenties
    -0.73
     poffe
    -0.70
    \{\\
    -0.70
     deſt
    -0.69
     Efq
    -0.68
     houſe
    -0.67
     occafion
    -0.67
     caufe
    -0.66
    POSITIVE LOGITS
    OnClickListener
    1.28
     ActionListener
    1.20
    ActionListener
    1.19
     OnClickListener
    0.99
    CompleteListener
    0.96
    MouseListener
    0.95
    TextWatcher
    0.90
    ClickListener
    0.89
    SuccessListener
    0.86
    Listener
    0.80
    Activations Density 0.033%

    No Known Activations