© 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. 17212
    Prev
    Next
    INDEX
    Explanations

    code-related function definitions and structure

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

    reader directly

    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
    DotNetBar
    -0.65
     ligiloj
    -0.59
    Tikang
    -0.59
     useAppContext
    -0.58
    PerformLayout
    -0.56
     surla
    -0.56
     JpaRepository
    -0.54
     <<<<<<<<<<<<<<
    -0.52
     AssemblyTitle
    -0.51
    httphttps
    -0.51
    POSITIVE LOGITS
    stream
    0.50
     stream
    0.48
    fjspx
    0.41
    GetEnumerator
    0.41
    Stream
    0.36
    ExecuteReader
    0.33
     Stream
    0.32
    Iterator
    0.32
     kayna
    0.32
    ostream
    0.31
    Activations Density 0.115%

    No Known Activations