© 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. 1247
    Prev
    Next
    INDEX
    Explanations

    references to technical or critical evaluations of films and their elements

    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
    +#+
    -0.66
    ConstraintMaker
    -0.65
     ujednoznacz
    -0.64
    CloseOperation
    -0.64
    GenerationType
    -0.63
     تضيفلها
    -0.62
    IUrlHelper
    -0.61
    WireFormatLite
    -0.61
    amaño
    -0.60
     Wiktionnaire
    -0.60
    POSITIVE LOGITS
     poor
    2.08
     lousy
    1.85
     terrible
    1.77
     crappy
    1.73
    poor
    1.72
     poorly
    1.70
     bad
    1.68
     worst
    1.64
     horrible
    1.64
    Poor
    1.63
    Activations Density 0.758%

    No Known Activations