Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 6990
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to web automation and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mon
    -0.49
     mon
    -0.49
    <eos>
    -0.45
     Mon
    -0.45
     senderos
    -0.44
    דור
    -0.44
     "
    -0.43
     me
    -0.43
     né
    -0.42
    진
    -0.41
    POSITIVE LOGITS
    WebElementEntity
    0.88
    AndroidJUnit
    0.84
    MessageOf
    0.84
     webdriver
    0.84
     ChromeDriver
    0.84
    ftagPool
    0.82
     ―――――
    0.81
     ſind
    0.80
    ########.
    0.79
    openqa
    0.79
    Activations Density 0.343%

    No Known Activations