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. 4-GEMMASCOPE-RES-16K
    6. 499
    Prev
    Next
    INDEX
    Explanations

    terms related to continuity and continuous processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.74
     éché
    -0.69
    andExpect
    -0.68
     flavors
    -0.67
     estekak
    -0.66
    درسة
    -0.65
    erráneo
    -0.65
    CellStyle
    -0.64
    PMailer
    -0.63
    SizeMode
    -0.63
    POSITIVE LOGITS
     continuous
    2.55
    Continuous
    2.46
     Continuous
    2.44
    continuous
    2.38
     continuously
    1.94
     contin
    1.86
     CONTIN
    1.81
     contín
    1.79
    CONTIN
    1.79
    contin
    1.76
    Activations Density 0.101%

    No Known Activations