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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 6692
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nothing."

    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
    TagHelpers
    -0.63
    λους
    -0.59
     AssemblyTitle
    -0.58
    orari
    -0.56
    estly
    -0.56
    estyles
    -0.54
    ณะ
    -0.52
     tornando
    -0.52
    しまう
    -0.51
     Mortuary
    -0.51
    POSITIVE LOGITS
     nothing
    3.69
    nothing
    3.43
     Nothing
    3.31
    Nothing
    3.30
     NOTHING
    2.95
    NOTHING
    2.73
     nothin
    2.29
     nichts
    2.09
     niets
    2.04
     rien
    2.02
    Activations Density 0.055%

    No Known Activations