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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101903
    Prev
    Next
    INDEX
    Explanations

    legal terminology and processes, particularly in relation to court decisions and appeals

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

    Common words and phrases that appear in technical, academic, or legal texts, often representing specific concepts within their domains like "time specified", "positive observation", "assent", "taken", "order", "secre(ted)", "sera", "antibiotics", "threat", "leaks", "market", "available", "negotiations", "treaty", "antibody".

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    DockStyle
    -0.40
    djangoproject
    -0.39
    unmodifiable
    -0.38
     propOrder
    -0.37
    todoList
    -0.37
    dataclass
    -0.36
     rit
    -0.36
    extAlignment
    -0.35
     selv
    -0.35
    Jereo
    -0.35
    POSITIVE LOGITS
    曖昧さ回避
    0.50
    LabelTagHelper
    0.49
     Italijani
    0.48
    AndEndTag
    0.46
     touristique
    0.45
     conducción
    0.45
    Bible
    0.44
     Biblical
    0.43
     conduite
    0.43
    OOTDTY
    0.42
    Activations Density 0.273%

    No Known Activations