© 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. 58555
    Prev
    Next
    INDEX
    Explanations

    references to exchanges and their interactions

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

    exchange followed by term, field, or split

    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
     AssemblyTitle
    -0.53
     strto
    -0.52
    Dermott
    -0.50
     المعيارى
    -0.48
     Ril
    -0.47
     Sahib
    -0.46
    httphttps
    -0.46
    NOPQRST
    -0.46
    principalColumn
    -0.46
     Punj
    -0.45
    POSITIVE LOGITS
     Exchange
    1.39
     exchange
    1.39
    exchange
    1.29
     EXCHANGE
    1.28
    Exchange
    1.27
     exchanges
    1.11
    EXCHANGE
    1.09
     Exchanges
    1.08
     exchanging
    0.93
     exchanged
    0.92
    Activations Density 0.010%

    No Known Activations