© 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 EvalsExportsinterp-engineNEWAPI 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. 21419
    Prev
    Next
    INDEX
    Explanations

    negations and contradictory phrases

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

    granularity variation system

    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
     disambiguazione
    -0.64
    存于互联网档案馆
    -0.59
    曖昧さ回避
    -0.56
     gynhyrchwyd
    -0.54
    kháu
    -0.53
    richTextPanel
    -0.53
     Económica
    -0.52
     BoxDecoration
    -0.52
    Чыгана
    -0.51
    contentLoaded
    -0.50
    POSITIVE LOGITS
    Join
    0.34
     Join
    0.32
    Dr
    0.32
    umenten
    0.32
    œ
    0.32
     Attention
    0.31
     OPP
    0.31
    "
    0.30
     ATT
    0.30
    丁
    0.29
    Activations Density 0.052%

    No Known Activations