© 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. 11-GEMMASCOPE-RES-16K
    11. 7772
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax elements related to functions, parameters, and data flow in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.38
     pleaſure
    -0.30
     themſelves
    -0.27
     querr
    -0.26
    hånd
    -0.25
    ſelf
    -0.25
    cemment
    -0.25
     intentos
    -0.24
    følgelig
    -0.24
    ennemi
    -0.24
    POSITIVE LOGITS
     '{@
    0.77
    iſchen
    0.73
    請繼續往下閱讀
    0.73
     queſto
    0.68
    rungsseite
    0.68
    rawDesc
    0.67
    EDEFAULT
    0.67
    SOUNDBITE
    0.66
    niſſe
    0.66
     endwhile
    0.65
    Activations Density 0.276%

    No Known Activations