© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101858
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial figures

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

    millions and billions

    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
    itoria
    -0.32
    ://
    -0.31
     K
    -0.30
    UGHTER
    -0.30
     Let
    -0.29
     V
    -0.29
     tag
    -0.27
    ナル
    -0.27
    因
    -0.26
                                   
    -0.26
    POSITIVE LOGITS
    AddTagHelper
    0.88
     Paglinawan
    0.86
     Signalez
    0.81
    rungsseite
    0.79
     nahilalakip
    0.76
     ModelExpression
    0.75
     ब्रेकडाउन
    0.73
    iſchen
    0.72
     CreateTagHelper
    0.70
    enterOuterAlt
    0.70
    Activations Density 0.025%

    No Known Activations