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. 19-GEMMASCOPE-RES-16K
    6. 3303
    Prev
    Next
    INDEX
    Explanations

    concepts related to diversity and variety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    machte
    -0.58
    izzard
    -0.51
     нат
    -0.47
    ارية
    -0.47
     inexist
    -0.44
     ces
    -0.44
     carré
    -0.44
    LETED
    -0.44
    IANS
    -0.43
    chable
    -0.43
    POSITIVE LOGITS
    各样的
    0.99
     BoxFit
    0.90
     assortment
    0.84
    EndProject
    0.79
    windowFixed
    0.79
     afield
    0.79
     backgrounds
    0.78
     flavors
    0.77
    NameInMap
    0.77
     genres
    0.76
    Activations Density 0.169%

    No Known Activations