© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104209
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and conditions related to defenses in legal cases

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

    Line breaks or section transitions in structured documents, often indicating the beginning of a new section or subsection.

    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
    CloseOperation
    -0.51
     Italijanski
    -0.47
    olstadt
    -0.45
    biskan
    -0.42
     Meksiku
    -0.41
    îtra
    -0.41
    mtrl
    -0.41
    #
    -0.38
    INTRODUCTION
    -0.37
     achievements
    -0.37
    POSITIVE LOGITS
    évaluateur
    0.58
    RegressionTest
    0.47
    verwijspagina
    0.47
    CardModule
    0.41
    الحياه
    0.41
    Jeografia
    0.40
    XmlType
    0.40
     Sünde
    0.39
     الحره
    0.38
     <<<<<<<<<<<<<<
    0.38
    Activations Density 0.029%

    No Known Activations