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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2185
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases centered around the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Пря
    -0.74
     Drapeau
    -0.64
     ostavi
    -0.63
    췄
    -0.62
    AfterClass
    -0.61
    perrt
    -0.60
    endaft
    -0.60
     épaules
    -0.58
     dépens
    -0.58
     doInBackground
    -0.57
    POSITIVE LOGITS
    ividual
    0.71
    hermosa
    0.66
    ámetro
    0.65
    [+]
    0.64
    +#+#
    0.64
    [toxicity=0]
    0.63
    坞
    0.63
    edades
    0.63
    CKS
    0.62
    NUMX
    0.62
    Activations Density 0.170%

    No Known Activations