Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11187
    Prev
    Next
    INDEX
    Explanations

    technical terms related to particle accelerators and their components

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

    Particle beams and acceleration

    np_acts-logits-general · gemini-2.0-flash

    particle accelerator and beam physics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.52
    ngrx
    -0.50
    msgstr
    -0.49
    তথ্যসূত্র
    -0.49
     autorytatywna
    -0.48
     Grund
    -0.47
    icism
    -0.47
     مرئيه
    -0.47
     Réponses
    -0.45
     crees
    -0.44
    POSITIVE LOGITS
     beam
    0.78
     accelerator
    0.67
     OnTriggerEnter
    0.66
    beam
    0.65
    guns
    0.65
     MeV
    0.64
     Italijanski
    0.62
     Bun
    0.62
     Moderato
    0.62
     keV
    0.62
    Activations Density 0.765%

    No Known Activations