© 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. 9-GEMMASCOPE-RES-16K
    11. 8809
    Prev
    Next
    INDEX
    Explanations

    references to CDs and related media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fulness
    -0.80
    IntoConstraints
    -0.74
    دانشنامهٔ
    -0.72
     estimés
    -0.70
    LLocation
    -0.69
    GenerationType
    -0.68
     Atti
    -0.67
    clientY
    -0.66
     Verg
    -0.65
    lorem
    -0.65
    POSITIVE LOGITS
     discs
    1.36
     CDs
    1.35
     CD
    1.32
     disc
    1.28
     cd
    1.27
     disks
    1.26
    CD
    1.17
     disk
    1.13
    disc
    1.06
    CDs
    1.05
    Activations Density 0.140%

    No Known Activations