© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4624
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ignore"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    KommentareTeilen
    -0.63
     المعيارى
    -0.63
    InstrumentedTest
    -0.61
    vel
    -0.58
    ngdoc
    -0.58
     VIAF
    -0.57
     babak
    -0.56
    Saf
    -0.55
    OGND
    -0.55
    ThroughAttribute
    -0.55
    POSITIVE LOGITS
     ignore
    3.11
     ignored
    2.87
     ignoring
    2.86
     ignores
    2.76
     Ignore
    2.68
    ignore
    2.44
     Ignoring
    2.40
    Ignoring
    2.21
    ignored
    2.13
    Ignore
    2.12
    Activations Density 0.104%

    No Known Activations