© 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. 21-GEMMASCOPE-RES-16K
    11. 1224
    Prev
    Next
    INDEX
    Explanations

    references to statistical values or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ack
    -0.43
    Pon
    -0.42
    its
    -0.42
    ver
    -0.40
    dol
    -0.39
    ika
    -0.38
    →
    -0.37
    zeigt
    -0.37
     dor
    -0.37
    mas
    -0.36
    POSITIVE LOGITS
    IsMutable
    1.00
    StoryboardSegue
    0.99
    XmlAccessType
    0.91
     tartalomajánló
    0.88
    ArrowToggle
    0.87
    EndProject
    0.84
    Datuak
    0.83
     AssemblyTitle
    0.81
    PARATUS
    0.81
    DoubleQuotes
    0.79
    Activations Density 0.686%

    No Known Activations