© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1193
    Prev
    Next
    INDEX
    Explanations

    references to the name "Cooper" in the context of scientific discussions or descriptions

    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
     almohada
    -0.40
     conferir
    -0.38
     comigo
    -0.35
     Anfrage
    -0.33
     understandable
    -0.32
     inclusión
    -0.32
    anterie
    -0.32
     Gespräche
    -0.32
     arcilla
    -0.31
     envelo
    -0.31
    POSITIVE LOGITS
    Cooper
    1.19
     Cooper
    1.13
     COOPER
    1.03
     cooper
    0.98
    cooper
    0.97
     cooperative
    0.79
     Cooperative
    0.77
    cooperative
    0.75
    Cooperative
    0.73
     cooperating
    0.71
    Activations Density 0.367%

    No Known Activations