© 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. 63046
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and keywords related to various scientific and computational concepts

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

    protein, hemocytes, silicon, pixel electronics, inactive, payline

    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
     فريبيس
    -0.64
     geweest
    -0.62
    XmlAccessType
    -0.62
     comigo
    -0.60
     belangrij
    -0.60
     zoude
    -0.59
    SequentialGroup
    -0.59
     vermelha
    -0.58
     leão
    -0.57
     techniczne
    -0.56
    POSITIVE LOGITS
    “-
    0.41
    -“
    0.41
    ,“
    0.38
    !—
    0.38
     setter
    0.38
     brus
    0.38
    期刊论文
    0.37
    Geplaatst
    0.37
     nonUne
    0.37
    -(-
    0.36
    Activations Density 0.348%

    No Known Activations