© 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. 2-GEMMASCOPE-RES-16K
    11. 15601
    Prev
    Next
    INDEX
    Explanations

    references to mechanisms in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optical
    -0.40
    Assigned
    -0.37
    relationship
    -0.36
     Agile
    -0.35
     Optical
    -0.34
     éclair
    -0.34
    Digital
    -0.34
    setLeft
    -0.33
    Stiff
    -0.33
     relationship
    -0.33
    POSITIVE LOGITS
     mechanism
    1.48
     Mechanism
    1.47
     mechanisms
    1.40
    mechanism
    1.39
    Mechanism
    1.36
     Mechanisms
    1.32
    Mechanisms
    1.29
     mécanisme
    1.23
     MECHAN
    1.21
     mecanismo
    1.13
    Activations Density 0.104%

    No Known Activations