© 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. 14579
    Prev
    Next
    INDEX
    Explanations

    HTML elements and formatting tags within a text document

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

    HTML tags and <start_of_turn>user

    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
     snippetHide
    -0.68
    WithIOException
    -0.57
     propOrder
    -0.56
    ########.
    -0.56
     "..\..\..\
    -0.54
     "..\..\
    -0.54
    ̈́
    -0.53
     EconPapers
    -0.52
    SequentialGroup
    -0.50
     IBOutlet
    -0.48
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.63
     explaining
    0.47
     étoit
    0.45
     pointing
    0.43
     étoient
    0.40
     contó
    0.38
    AccessorTable
    0.36
    ChrTalk
    0.36
    Explain
    0.36
     explain
    0.36
    Activations Density 0.014%

    No Known Activations