© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 625
    Prev
    Next
    INDEX
    Explanations

    terms related to plaintiffs and defendants in legal documents

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

    legal and bureaucratic language related to court cases and legal proceedings.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    httphttps
    -0.66
     pinulongan
    -0.64
     يتيمه
    -0.63
    цездатний
    -0.60
    tableFuture
    -0.56
    URLException
    -0.56
     للاسماء
    -0.55
     surla
    -0.48
    GenerationType
    -0.48
    avigation
    -0.48
    POSITIVE LOGITS
     candidate
    0.61
     bénéficiaire
    0.61
     Candidate
    0.58
    participant
    0.57
     Appellee
    0.57
     respondent
    0.57
    candidate
    0.56
     applicant
    0.56
    Applicant
    0.56
     Applicant
    0.55
    Activations Density 0.626%

    No Known Activations