© 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
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1993
    Prev
    Next
    INDEX
    Explanations

    biological processes and chemical compositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sprung
    -0.42
     Kalt
    -0.32
    bes
    -0.31
     Bes
    -0.31
    col
    -0.30
     Col
    -0.29
    wnia
    -0.29
     su
    -0.29
     Whit
    -0.28
     Bra
    -0.28
    POSITIVE LOGITS
     Paglinawan
    0.81
    ConstraintMaker
    0.74
    KommentareTeilen
    0.72
    MessageTagHelper
    0.65
     betweenstory
    0.64
     defaultstate
    0.63
    esModule
    0.62
    ValueStyle
    0.61
    ReusableCell
    0.61
     ujednoznacz
    0.60
    Activations Density 2.160%

    No Known Activations