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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 13561
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to programming and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accounting
    -0.40
     måneder
    -0.39
     и
    -0.38
    couverte
    -0.37
    **
    -0.37
    Accounts
    -0.36
     municipales
    -0.36
     jours
    -0.36
    خلا
    -0.36
     i
    -0.35
    POSITIVE LOGITS
    £
    0.85
     >=",
    0.78
     AppColors
    0.70
     تانيه
    0.70
    MENAFN
    0.70
     Efq
    0.69
     MainAxisSize
    0.69
    uxxxx
    0.69
    WithIOException
    0.69
     Majefty
    0.67
    Activations Density 0.024%

    No Known Activations