© 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. 36-GEMMASCOPE-RES-16K
    11. 6228
    Prev
    Next
    INDEX
    Explanations

    references to various types of analyses and experimental methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.50
    новниш
    -0.48
    windowFixed
    -0.45
    ifikationer
    -0.44
    WillAppear
    -0.44
    Дереккөздер
    -0.43
     réglable
    -0.42
     createState
    -0.42
     bénévol
    -0.40
    ⤹
    -0.40
    POSITIVE LOGITS
     performed
    2.41
     Performed
    2.02
     conducted
    2.00
    performed
    1.88
     perform
    1.88
     PERFORM
    1.84
    Performed
    1.84
     performing
    1.82
     performs
    1.79
     Perform
    1.75
    Activations Density 1.522%

    No Known Activations