© 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. 40-GEMMASCOPE-RES-16K
    11. 3633
    Prev
    Next
    INDEX
    Explanations

    numerical values or patterns resembling data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     løpet
    -0.27
     gedachten
    -0.17
     vė
    -0.14
     daqui
    -0.13
     gydy
    -0.13
     météoro
    -0.13
    DESCRIP
    -0.11
    stående
    -0.11
     Inscrivez
    -0.11
     detaljer
    -0.10
    POSITIVE LOGITS
    oredCriteria
    0.89
    ⓧ
    0.85
     kasarigan
    0.84
    ſchaft
    0.84
    iſchen
    0.83
    ISupport
    0.83
    Xna
    0.81
    :✨
    0.80
     dieſer
    0.78
    fjspx
    0.78
    Activations Density 0.359%

    No Known Activations