© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 58281
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical or statistical values and measures

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

    reference markers

    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
    ="@+
    -0.47
    >{@
    -0.46
    simpleType
    -0.46
    queryInterface
    -0.44
     "..\..\..\
    -0.44
    ✨:
    -0.44
    InputBorder
    -0.42
     ब्रेकडाउन
    -0.41
    writeField
    -0.40
    riwal
    -0.40
    POSITIVE LOGITS
    脚注
    3.13
    脚注の使い方
    1.94
    外部リンク
    1.72
    日閲覧
    1.27
    각주
    1.24
    出典
    1.08
    関連項目
    0.79
     링크
    0.74
    注釈
    0.63
    外部連結
    0.62
    Activations Density 0.000%

    No Known Activations