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. 9-GEMMASCOPE-RES-16K
    6. 1374
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical terms and symbols, particularly in the context of graph theory or structured data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chứ
    -0.56
     treo
    -0.52
    DateTimePicker
    -0.52
    inato
    -0.52
     vân
    -0.50
    enumi
    -0.49
    おそ
    -0.48
     late
    -0.48
     Last
    -0.48
    Last
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.77
    unächst
    0.75
     getFirst
    0.72
    PropertyChanging
    0.70
     primeiros
    0.69
    Primero
    0.69
    uerst
    0.69
     eerste
    0.67
    getFirst
    0.67
    FIRST
    0.67
    Activations Density 1.612%

    No Known Activations