© 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. 22-GEMMASCOPE-RES-16K
    11. 5961
    Prev
    Next
    INDEX
    Explanations

    code snippets and annotations related to programming and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berdayakan
    -0.45
    AddTagHelper
    -0.43
    AnimationsModule
    -0.37
    writerow
    -0.35
     Seulement
    -0.32
     ocupado
    -0.32
     voici
    -0.32
    További
    -0.31
    ckså
    -0.30
    TypedDataSet
    -0.30
    POSITIVE LOGITS
     cref
    0.89
     '{@
    0.72
    httphttps
    0.68
    Vidite
    0.66
     {@
    0.65
    :✨
    0.64
    >{@
    0.61
    Personendaten
    0.60
    nameof
    0.60
    eqn
    0.60
    Activations Density 0.534%

    No Known Activations