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. 16-GEMMASCOPE-RES-16K
    6. 1509
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to internet connectivity and networking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens related to the "internet" or "net"

    np_acts-logits-general · gemini-2.0-flash

    internet protocol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.73
     ExecuteAsync
    -0.61
    TEMPO
    -0.60
     createSlice
    -0.59
    rungsseite
    -0.58
    AMC
    -0.56
    °•
    -0.56
    msgTypes
    -0.54
    formas
    -0.53
    PTS
    -0.53
    POSITIVE LOGITS
     Internet
    1.14
     internet
    1.07
     net
    1.06
     NET
    1.05
     Net
    1.01
     INTERNET
    0.99
    Internet
    0.98
     nets
    0.94
    internet
    0.93
    net
    0.90
    Activations Density 0.176%

    No Known Activations