© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 156
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs in programming

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

    Text after specific punctuation or tokens

    np_acts-logits-general · gemini-2.0-flash

    handling interruption and returns

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ftagPool
    -0.51
    expandindo
    -0.49
     fino
    -0.45
    isielt
    -0.43
     publicação
    -0.43
     confiança
    -0.42
     suprême
    -0.41
    verifyException
    -0.41
     zufolge
    -0.41
    zőkönyv
    -0.41
    POSITIVE LOGITS
    ruptedException
    0.78
    aarrggbb
    0.44
     mids
    0.40
     doInBackground
    0.38
    onViewCreated
    0.38
    HomeAsUpEnabled
    0.37
    QMetaType
    0.37
    umab
    0.36
    Interrupt
    0.35
    astify
    0.35
    Activations Density 0.293%

    No Known Activations