© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5517
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or inquiry about correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Correct" and "incorrect" statements

    np_acts-logits-general · gemini-2.0-flash

    correctness or incorrectness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dostępne
    -0.34
    お待ち
    -0.33
    Ventajas
    -0.32
     związane
    -0.31
    ventajas
    -0.30
     możesz
    -0.30
     współpra
    -0.29
     jednocześnie
    -0.29
     realizacji
    -0.29
     aans
    -0.29
    POSITIVE LOGITS
     correct
    1.91
    correct
    1.69
     Correct
    1.59
    Correct
    1.58
     correctly
    1.52
     incorrect
    1.50
     CORRECT
    1.45
     wrong
    1.41
    correctly
    1.37
    正确
    1.34
    Activations Density 0.428%

    No Known Activations