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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8200
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court proceedings and judgments.

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

    legal terms and phrases related to court cases and legal proceedings.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to legal accusations, charges, and court proceedings.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    "against" follows certain verbs/nouns

    np_acts-logits-general · gemini-2.0-flash

    charges 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
    \{\\
    -0.59
    AnchorStyles
    -0.55
    Notifier
    -0.54
    ACIONAL
    -0.51
     صوتيه
    -0.51
    󠁣
    -0.49
    iper
    -0.48
      (
    -0.47
    ekte
    -0.47
     ujednoznacz
    -0.47
    POSITIVE LOGITS
     against
    3.92
    against
    3.38
     Against
    3.34
    Against
    3.27
     AGAINST
    2.90
     gegen
    2.46
     contre
    2.35
     против
    2.08
     againſt
    1.98
     tegen
    1.95
    Activations Density 0.700%

    No Known Activations