© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55655
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting symbols used in coding or markup languages

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

    link separator rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     насељу
    -1.02
    RegressionTest
    -1.00
    principalColumn
    -0.97
     betweenstory
    -0.96
     MainAxisSize
    -0.94
     propOrder
    -0.94
    parsedMessage
    -0.94
    Personendaten
    -0.93
     disambiguazione
    -0.91
    transQ
    -0.90
    POSITIVE LOGITS
    ’
    0.35
     \
    0.34
     whole
    0.32
    '
    0.31
     new
    0.31
     sheet
    0.31
     text
    0.28
     $\
    0.28
     
    0.28
     deep
    0.27
    Activations Density 0.031%

    No Known Activations