© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2236
    Prev
    Next
    INDEX
    Explanations

    words related to the Flaivirus family, particularly highlighting different variants and their characteristics

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

    starting with "fla" or "fl"

    np_acts-logits-general · gemini-2.0-flash

    words starting with fl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.56
    IGENCE
    -0.54
     EconPapers
    -0.51
    
    -0.51
     InputDecoration
    -0.51
     للمعارف
    -0.49
    UVWXYZ
    -0.47
     nakalista
    -0.44
     Autorisations
    -0.43
     tetrach
    -0.42
    POSITIVE LOGITS
     fl
    0.68
     FL
    0.66
     Fl
    0.60
    fl
    0.60
    Fla
    0.58
    FLO
    0.58
    FL
    0.58
     Fla
    0.57
     Flu
    0.57
    fla
    0.56
    Activations Density 0.142%

    No Known Activations