© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8845
    Prev
    Next
    INDEX
    Explanations

    questions and suggestions in a conversational context

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

    Code-related or XML-related text after "A:" or "Q:"

    np_acts-logits-general · gemini-2.0-flash

    you can envision

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    HasForeignKey
    -0.67
     AssemblyCulture
    -0.63
    InitStruct
    -0.60
    CodeAttribute
    -0.60
    المناصب
    -0.59
     المعيارى
    -0.58
    LookAnd
    -0.57
    yntaxException
    -0.56
     دیکھیے
    -0.55
    पया
    -0.54
    POSITIVE LOGITS
     envision
    0.36
    向
    0.35
     kickoff
    0.32
     mema
    0.32
     outlining
    0.32
    estart
    0.31
     detailing
    0.31
    imagined
    0.31
     starten
    0.29
     מתח
    0.29
    Activations Density 0.047%

    No Known Activations