© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86193
    Prev
    Next
    INDEX
    Explanations

    nested structures and mathematical expressions

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

    code with punctuation

    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
     للاسماء
    -0.79
     nonUne
    -0.74
    Personendaten
    -0.71
     betweenstory
    -0.61
     invokingState
    -0.61
     myſelf
    -0.58
     ujednoznacz
    -0.55
     تضيفلها
    -0.55
    országban
    -0.54
     незавершена
    -0.54
    POSITIVE LOGITS
    thenReturn
    0.42
    ?}",
    0.37
     så
    0.36
    __(/*!
    0.33
    runApp
    0.33
     micro
    0.31
    ]{\
    0.31
     $\
    0.31
    Så
    0.30
     the
    0.30
    Activations Density 0.019%

    No Known Activations