© 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. 35-GEMMASCOPE-RES-16K
    11. 7574
    Prev
    Next
    INDEX
    Explanations

    data related to sports statistics and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esercito
    -0.35
     ejército
    -0.35
     orgánico
    -0.32
     Architektur
    -0.32
     arquitetura
    -0.32
     orgánica
    -0.32
    ⓧ
    -0.32
     policial
    -0.31
     défense
    -0.31
     corazones
    -0.30
    POSITIVE LOGITS
     receivers
    1.13
     receiver
    1.09
     receptions
    1.03
     reception
    1.01
     Receiver
    1.00
     catches
    0.98
     RECE
    0.95
     catching
    0.94
     Reception
    0.94
     recep
    0.93
    Activations Density 0.196%

    No Known Activations