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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 10902
    Prev
    Next
    INDEX
    Explanations

    terms related to wave functions and quantum mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дото
    -0.67
    ktop
    -0.65
    どく
    -0.63
    iosync
    -0.61
     Isi
    -0.61
    DOUT
    -0.59
     Southgate
    -0.59
    nsics
    -0.58
    },[])
    -0.58
     FormControl
    -0.58
    POSITIVE LOGITS
     wave
    3.44
    wave
    3.20
     Wave
    3.19
     waves
    3.07
    Wave
    3.06
     WAVE
    2.97
    waves
    2.77
     Waves
    2.76
    WAVE
    2.70
    Waves
    2.47
    Activations Density 0.074%

    No Known Activations