© 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. 105934
    Prev
    Next
    INDEX
    Explanations

    code-related structures and function declarations

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

    Symbols, special characters, or notation used in mathematical expressions, scientific formulas, code syntax, or scientific naming convention.

    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
    sidemargin
    -0.57
    RegistryLite
    -0.45
     lenker
    -0.45
     للمعارف
    -0.43
     ExecuteAsync
    -0.40
     EconPapers
    -0.40
    LookAnd
    -0.39
     kasarigan
    -0.39
    testcase
    -0.36
    InputBorder
    -0.36
    POSITIVE LOGITS
    WebVitals
    0.59
    rungsseite
    0.57
     CreateTagHelper
    0.54
    enumii
    0.53
     мәкал
    0.52
    .*")]
    0.50
    ->___
    0.49
    
    0.48
    enumi
    0.48
    kwür
    0.48
    Activations Density 0.482%

    No Known Activations