© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6665
    Prev
    Next
    INDEX
    Explanations

    legal terminology and jargon related to court proceedings and legal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.27
    tagHelperRunner
    -1.20
    TestingModule
    -0.96
     صوتيه
    -0.94
    findpost
    -0.85
     AssemblyCulture
    -0.82
    FormTagHelper
    -0.78
    OGND
    -0.77
     contextLoads
    -0.76
     للاسماء
    -0.74
    POSITIVE LOGITS
    Mutagenicity
    0.45
    
    0.44
     createSprite
    0.42
    semantics
    0.41
    ItemLayout
    0.41
     tồn
    0.39
    ↵↵
    0.38
    Zdroje
    0.38
     ...
    0.38
     $("#
    0.38
    Activations Density 2.717%

    No Known Activations