© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14385
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to particle physics and the dynamics of particle interactions

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

    Particle physics events and measurements

    np_acts-logits-general · gemini-2.0-flash

    fermion pair cross section

    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
    RefNanny
    -0.64
    <?
    -0.64
    AlterField
    -0.63
    ftagPool
    -0.60
    bital
    -0.59
    EndInit
    -0.58
    NewUrlParser
    -0.58
    BaseAdapter
    -0.58
    ########.
    -0.57
    WebServlet
    -0.57
    POSITIVE LOGITS
     jets
    0.60
     events
    0.60
    jets
    0.59
     cross
    0.58
    Jets
    0.55
    jet
    0.53
     collisions
    0.49
    Jet
    0.49
     jet
    0.49
     eventi
    0.49
    Activations Density 0.584%

    No Known Activations