© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1166
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "erasing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insp
    -0.70
     Caval
    -0.62
    InjectMocks
    -0.60
     strut
    -0.59
     turi
    -0.58
    Gemeinden
    -0.57
    Jumbo
    -0.56
    quinone
    -0.56
    UDO
    -0.56
     propor
    -0.56
    POSITIVE LOGITS
     Er
    2.54
     er
    2.47
    Er
    2.44
     ER
    1.80
     Erm
    1.39
     Erskine
    1.28
     Eras
    1.26
     Eri
    1.20
    ER
    1.18
    Erm
    1.18
    Activations Density 0.168%

    No Known Activations