© 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. 33-GEMMASCOPE-RES-16K
    11. 6462
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to specific group characteristics and categories

    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
    这是
    -0.27
     stating
    -0.25
     Femen
    -0.24
    териалы
    -0.23
    scryfall
    -0.22
     dating
    -0.22
     termin
    -0.22
    pdp
    -0.22
    あれ
    -0.21
     kiện
    -0.21
    POSITIVE LOGITS
     include
    2.69
     includes
    2.52
     Include
    2.23
     Includes
    2.14
     incluem
    2.13
     incluye
    2.11
     inclui
    2.05
     incluyen
    2.03
    includes
    2.02
    Includes
    1.99
    Activations Density 0.826%

    No Known Activations