© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4843
    Prev
    Next
    INDEX
    Explanations

    structured programming elements such as functions, methods, and classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.48
    XmlAccessorType
    -0.43
     enfans
    -0.41
    󠁿
    -0.40
     >=",
    -0.37
    enfance
    -0.36
     laquelle
    -0.36
     архивлан
    -0.36
    তথ্যসূত্র
    -0.35
    })$}
    -0.34
    POSITIVE LOGITS
    ########.
    0.68
    +#+
    0.67
     autorytatywna
    0.59
    
    0.52
    toMatchSnapshot
    0.52
    lwjgl
    0.51
    ual
    0.51
    ular
    0.51
    Rü
    0.51
    vesti
    0.50
    Activations Density 0.292%

    No Known Activations