© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11547
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to figures in scientific contexts

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

    Numbers within brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers and range delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     taler
    -0.45
     numériques
    -0.44
     so
    -0.40
     meaning
    -0.39
     File
    -0.39
     god
    -0.39
     God
    -0.38
    File
    -0.38
     gekomen
    -0.38
     hukum
    -0.37
    POSITIVE LOGITS
    
    0.97
    出版年
    0.93
    UserScript
    0.90
    LookAnd
    0.85
    Personendaten
    0.81
    CloseOperation
    0.77
    SerializedSize
    0.77
    fjspx
    0.76
     OFDb
    0.76
     doInBackground
    0.76
    Activations Density 0.306%

    No Known Activations