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. 2-GEMMASCOPE-RES-16K
    6. 6298
    Prev
    Next
    INDEX
    Explanations

    terms related to guarantees and warranties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    唯
    -0.61
    classnames
    -0.54
     zur
    -0.54
    cyj
    -0.52
     BEC
    -0.51
    چسب
    -0.50
    PyExc
    -0.50
    fcntl
    -0.49
    Lage
    -0.48
    TDG
    -0.48
    POSITIVE LOGITS
     assure
    2.51
     assured
    2.47
     assures
    2.34
     guarantee
    2.27
     assuring
    2.23
     assurance
    2.13
     guaranteed
    2.12
     guarantees
    2.12
     assurances
    2.08
    assured
    2.06
    Activations Density 0.073%

    No Known Activations