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. 24-GEMMASCOPE-RES-16K
    6. 8307
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and contributions

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

    Belgium or Belgian things

    np_acts-logits-general · gemini-2.0-flash

    Belgium and Belgian cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bridgeport
    -0.53
    っこう
    -0.53
     Ventura
    -0.51
     Whittier
    -0.51
    stdc
    -0.49
     Udaipur
    -0.49
     odkazy
    -0.49
     Forder
    -0.49
     Oakland
    -0.48
     Severn
    -0.48
    POSITIVE LOGITS
     Belgian
    1.10
     Belgium
    1.10
    Belgium
    1.03
    Belgian
    1.01
     Brussels
    1.00
     Flemish
    0.96
     Belgi
    0.93
    Brussels
    0.92
     Flanders
    0.90
     Antwerp
    0.90
    Activations Density 0.120%

    No Known Activations