© 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. 35-GEMMASCOPE-RES-16K
    11. 10728
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical estimation and medical outcomes

    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
     propOrder
    -0.63
    новниш
    -0.61
    brigens
    -0.60
    antaranya
    -0.52
    colgante
    -0.51
     CanadaChoose
    -0.51
    ſſung
    -0.51
    niſſe
    -0.50
    kháu
    -0.50
    㤵
    -0.50
    POSITIVE LOGITS
     rather
    4.16
     instead
    3.77
    rather
    3.58
    instead
    3.36
     plutôt
    3.33
     Rather
    3.30
    Rather
    3.27
     zamiast
    3.03
     anstatt
    3.00
    Instead
    2.98
    Activations Density 2.621%

    No Known Activations