Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11155
    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 @ 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
    AccessorTable
    -0.71
    KommentareTeilen
    -0.71
     fær
    -0.66
     المعيارى
    -0.65
     @"/
    -0.65
     modelAndView
    -0.65
     Roderick
    -0.64
     Audiodateien
    -0.63
     AssemblyProduct
    -0.63
    vel
    -0.63
    POSITIVE LOGITS
     ignore
    2.70
     ignored
    2.53
     ignoring
    2.50
     ignores
    2.40
     Ignore
    2.40
    ignore
    2.26
     Ignoring
    2.06
     ignor
    2.01
    ignored
    1.96
    Ignore
    1.95
    Activations Density 0.067%

    No Known Activations