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. 4377
    Prev
    Next
    INDEX
    Explanations

    phrases related to managing and organizing notifications and content in a user interface context

    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
    ScopeManager
    -0.59
     FishBase
    -0.56
     незавершена
    -0.54
    webElementGuid
    -0.50
     muualla
    -0.50
    ství
    -0.50
    ulemon
    -0.50
    fjspx
    -0.50
     whir
    -0.50
    Personendaten
    -0.49
    POSITIVE LOGITS
    的
    1.03
    的自
    0.81
    的中
    0.80
    的大
    0.79
    的外
    0.78
    的新
    0.77
    的美
    0.77
    的高
    0.77
    의
    0.76
    的有
    0.76
    Activations Density 0.074%

    No Known Activations