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. 6705
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and controversial legal issues

    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
     فريبيس
    -0.89
     Bourgoin
    -0.74
    ChildScrollView
    -0.70
     estekak
    -0.66
    setPixel
    -0.66
    #+#
    -0.66
     lenker
    -0.65
    Démographie
    -0.63
     Sver
    -0.63
     Exactos
    -0.61
    POSITIVE LOGITS
     Law
    1.02
    Law
    0.85
    RenderAtEndOf
    0.84
     controversial
    0.72
     LAW
    0.68
    versial
    0.68
    HtmlAttribute
    0.65
    PRWEB
    0.60
    .__
    0.59
    ukan
    0.59
    Activations Density 0.085%

    No Known Activations