© 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. 75773
    Prev
    Next
    INDEX
    Explanations

    elements of structured text formatting, such as brackets and asterisks

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

    code snippets and section headers

    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
     ComVisible
    -0.75
    хьтан
    -0.65
    delwed
    -0.64
     bezeichneter
    -0.64
    WaitGroup
    -0.62
     للاسماء
    -0.62
    BeginContext
    -0.61
    олові
    -0.60
     <>",
    -0.59
     AssemblyVersion
    -0.58
    POSITIVE LOGITS
    Vision
    0.36
     Tivoli
    0.35
    True
    0.35
    {'
    0.35
    Level
    0.35
    <strong>
    0.35
     mission
    0.34
    Os
    0.34
    Entry
    0.34
    Le
    0.34
    Activations Density 0.012%

    No Known Activations