© 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. 9-GEMMASCOPE-RES-131K
    6. 12524
    Prev
    Next
    INDEX
    Explanations

    clauses and phrases that specify conditions or characteristics

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

    which followed by results, occurred, will, is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chieht
    -0.57
    تقاوى
    -0.56
    principalColumn
    -0.53
    HtmlAttribute
    -0.53
    adaptiveStyles
    -0.53
    UnsafeEnabled
    -0.52
     queſta
    -0.48
     defStyle
    -0.48
    IndentedString
    -0.48
    Bioaccumulative
    -0.47
    POSITIVE LOGITS
    wohnt
    0.40
     nào
    0.38
     sewn
    0.38
    もしれません
    0.37
    ++]
    0.35
     является
    0.34
    ame
    0.34
     Drs
    0.34
     audio
    0.34
    eters
    0.34
    Activations Density 0.385%

    No Known Activations