© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4839
    Prev
    Next
    INDEX
    Explanations

    specific data structures or models in technical documents

    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
    verwijspagina
    -1.07
    GEBURTSDATUM
    -1.05
     WaitForSeconds
    -1.02
    Sucesor
    -1.01
    Tikang
    -0.99
     bezeichneter
    -0.96
    awtextra
    -0.96
     كومونز
    -0.93
    \}\\
    -0.93
    ंदीखरीदारी
    -0.93
    POSITIVE LOGITS
    1
    1.43
    0
    1.07
    3
    0.96
    9
    0.91
    5
    0.91
    6
    0.89
    7
    0.88
    2
    0.88
    8
    0.86
    4
    0.83
    Activations Density 0.087%

    No Known Activations