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. 25-GEMMASCOPE-RES-16K
    6. 3844
    Prev
    Next
    INDEX
    Explanations

    words related to Azerbaijani cultural elements and musical instruments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.81
    SequentialGroup
    -0.56
     ++)
    -0.55
    endphp
    -0.47
     חיצוניים
    -0.47
     continuant
    -0.47
    IBarButtonItem
    -0.47
     ComVisible
    -0.46
    OfWork
    -0.46
    FontOfSize
    -0.46
    POSITIVE LOGITS
    Obrázky
    0.60
     ویکی‌پدیا
    0.55
     ExecuteAsync
    0.53
    Portale
    0.51
     оригіналу
    0.47
    couz
    0.46
    WebpackPlugin
    0.46
     laft
    0.44
    haustible
    0.44
     roman
    0.43
    Activations Density 0.051%

    No Known Activations