© 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. 1-GEMMASCOPE-RES-16K
    6. 2280
    Prev
    Next
    INDEX
    Explanations

    references to CR (critical response) in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.38
    illoma
    -0.35
    bisoft
    -0.35
    posy
    -0.35
     Poplar
    -0.34
     referrerpolicy
    -0.34
     yPos
    -0.33
    assertj
    -0.33
     Stirn
    -0.33
     posY
    -0.32
    POSITIVE LOGITS
     CR
    2.08
     Cr
    1.98
     cr
    1.96
    CR
    1.88
    Cr
    1.83
    cr
    1.74
     cri
    1.56
     Cran
    1.55
     Kr
    1.55
    Cran
    1.55
    Activations Density 0.330%

    No Known Activations