© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13781
    Prev
    Next
    INDEX
    Explanations

    references to the Hall of Fame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.51
     titolata
    -0.48
     spagno
    -0.45
     Meksiku
    -0.44
    Essentially
    -0.43
    eapon
    -0.42
    Recommendation
    -0.42
     znam
    -0.42
     دیکھیے
    -0.41
     GenerationType
    -0.41
    POSITIVE LOGITS
     contest
    0.83
     contests
    0.82
     Hall
    0.80
     hall
    0.72
     Contest
    0.71
     contesting
    0.70
    Hall
    0.68
     dispute
    0.67
    Contest
    0.65
    contest
    0.64
    Activations Density 0.122%

    No Known Activations