© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10408
    Prev
    Next
    INDEX
    Explanations

    references to workout plans and the structure of fitness programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.70
     cho
    -0.52
    __(/*!
    -0.46
    toBeTruthy
    -0.46
     yym
    -0.45
     UIFont
    -0.43
     quả
    -0.40
     ska
    -0.38
    tractor
    -0.38
     t
    -0.37
    POSITIVE LOGITS
    RegressionTest
    0.75
     nahilalakip
    0.74
     Walkover
    0.67
    saraba
    0.65
     остальных
    0.65
     Meksiku
    0.64
     remaining
    0.64
    reportWebVitals
    0.63
     остальные
    0.62
    SharedDtor
    0.61
    Activations Density 0.635%

    No Known Activations