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. 21-GEMMASCOPE-RES-16K
    6. 12610
    Prev
    Next
    INDEX
    Explanations

    military tactics and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.56
     ensaio
    -0.54
     Astronom
    -0.50
     vetorial
    -0.49
     abstrato
    -0.48
     doh
    -0.47
     Potsdam
    -0.46
    EndContext
    -0.46
     propOrder
    -0.46
     Wap
    -0.46
    POSITIVE LOGITS
     Special
    1.01
     special
    0.93
    Special
    0.92
     elite
    0.87
    special
    0.84
     commando
    0.81
     SEAL
    0.77
    elite
    0.73
     Elite
    0.73
     SPECIAL
    0.73
    Activations Density 0.251%

    No Known Activations