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. 9582
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal concepts and professionals

    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
    MemoryWarning
    -0.88
    VIAF
    -0.80
    RenderAtEndOf
    -0.75
     CreateTagHelper
    -0.74
    InjectAttribute
    -0.69
     mostrarse
    -0.66
     enriquec
    -0.66
     تضيفلها
    -0.64
    prägt
    -0.63
    帖最后由
    -0.62
    POSITIVE LOGITS
     legal
    4.62
     Legal
    4.18
    Legal
    4.12
    legal
    4.05
     LEGAL
    3.81
    LEGAL
    3.38
     legales
    2.84
     legally
    2.77
     legale
    2.76
     légal
    2.46
    Activations Density 0.092%

    No Known Activations