© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 836
    Prev
    Next
    INDEX
    Explanations

    technical terms and error messages related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jona
    -0.50
    Anhalt
    -0.44
     ‘
    -0.43
     Sarah
    -0.43
    ighting
    -0.42
     requ
    -0.41
    ierungen
    -0.41
     Elev
    -0.40
     Jol
    -0.40
     '
    -0.40
    POSITIVE LOGITS
    의
    0.89
    ၏
    0.60
    的
    0.60
     的
    0.57
    */].
    0.57
    ның
    0.54
     queſta
    0.54
     của
    0.52
     की
    0.51
     való
    0.51
    Activations Density 0.013%

    No Known Activations