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. 2-GEMMASCOPE-RES-16K
    6. 4853
    Prev
    Next
    INDEX
    Explanations

    references to spiritual authority and scriptural passages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.61
    pegno
    -0.58
     Curs
    -0.55
     Knie
    -0.53
     päiv
    -0.52
     CSIRO
    -0.51
     šķ
    -0.50
    getahuan
    -0.50
     purpoſe
    -0.49
     reaſon
    -0.49
    POSITIVE LOGITS
    lossians
    1.04
     Thessal
    0.70
    iastes
    0.68
     препратки
    0.62
    Hebrews
    0.59
    Revelation
    0.58
     calendriers
    0.58
     Corintios
    0.58
     >=",
    0.56
     Luke
    0.56
    Activations Density 0.204%

    No Known Activations