© 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. 6189
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing repetition or insistence

    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
    kano
    -0.89
     Hale
    -0.71
     Schoen
    -0.67
     Hernando
    -0.66
    __.
    -0.65
    што
    -0.65
     Koc
    -0.65
    ZI
    -0.64
     Purdy
    -0.64
    \_\_
    -0.64
    POSITIVE LOGITS
    AGAIN
    1.06
     AGAIN
    1.03
     Again
    1.02
    Again
    1.02
     again
    1.00
    again
    0.96
    TestingModule
    0.88
    jsdelivr
    0.87
     Audiodateien
    0.85
    igshid
    0.85
    Activations Density 0.046%

    No Known Activations