© 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. 20-GEMMASCOPE-RES-16K
    11. 5947
    Prev
    Next
    INDEX
    Explanations

    terms related to legal principles and judicial reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Arguments against or in favor of something

    np_acts-logits-general · gemini-2.0-flash

    weighs in favor or against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.51
    uram
    -0.49
    ್
    -0.47
     dönüş
    -0.47
     Seelen
    -0.46
    enuine
    -0.46
    ICD
    -0.45
     Nachfolger
    -0.43
     Umgang
    -0.43
     programme
    -0.42
    POSITIVE LOGITS
     favor
    2.27
     favour
    2.25
     favoring
    2.07
    favor
    1.89
     favors
    1.88
     FAVOR
    1.86
     Favor
    1.83
     favours
    1.78
    Favor
    1.71
     favore
    1.68
    Activations Density 0.350%

    No Known Activations