© 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. 7887
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to criminal justice and evidence

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

    Legal and evidentiary standards

    np_acts-logits-general · gemini-2.0-flash

    legal standards and tests

    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
     bienvenue
    -0.51
    rfloor
    -0.50
    々木
    -0.50
     privilegi
    -0.48
    hidupan
    -0.48
     vastu
    -0.48
     fondly
    -0.48
    gaw
    -0.47
    ยว
    -0.47
    "]),
    -0.47
    POSITIVE LOGITS
     criteria
    0.77
     criterion
    0.77
     defaultstate
    0.73
     threshold
    0.72
     prouver
    0.72
     burden
    0.71
     критери
    0.71
    IsMutable
    0.68
     test
    0.68
     probar
    0.68
    Activations Density 2.005%

    No Known Activations