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. 10-GEMMASCOPE-RES-16K
    6. 3095
    Prev
    Next
    INDEX
    Explanations

    references to film credits and contributions such as directors, producers, and production teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.84
     дописавши
    -0.81
    rungsseite
    -0.81
    +#+#
    -0.78
    archiviato
    -0.74
     Paglinawan
    -0.71
     itſelf
    -0.70
     saveiro
    -0.69
     iſt
    -0.67
     >=",
    -0.66
    POSITIVE LOGITS
     
    0.66
    MemoryWarning
    0.56
      
    0.56
    同上
    0.54
     (
    0.51
    Trama
    0.49
     …
    0.49
    :
    0.49
    ?
    0.48
     “
    0.47
    Activations Density 0.450%

    No Known Activations