© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 2831
    Prev
    Next
    INDEX
    Explanations

    the concept of ignoring or neglecting various subjects or warnings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    d
    -0.68
     fær
    -0.67
     AssemblyProduct
    -0.64
    T
    -0.63
    S
    -0.63
    F
    -0.63
    B
    -0.62
    V
    -0.61
    t
    -0.61
    BeforeAll
    -0.59
    POSITIVE LOGITS
     ignoring
    1.39
     ignore
    1.36
     Ignore
    1.34
     ignored
    1.31
     ignores
    1.30
    gnore
    1.25
    Ignored
    1.14
     Ignoring
    1.13
    ignore
    1.12
     disregarded
    1.11
    Activations Density 0.150%

    No Known Activations