© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2886
    Prev
    Next
    INDEX
    Explanations

    elements related to effort and success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.58
    PhysRev
    -0.53
     descans
    -0.51
    ंदीखरीदारी
    -0.50
     للمعارف
    -0.49
    chrom
    -0.49
     sentito
    -0.47
    ţiei
    -0.47
    rak
    -0.47
     fosse
    -0.47
    POSITIVE LOGITS
    UnusedPrivate
    0.69
    RenderAtEndOf
    0.66
    archiviato
    0.58
    })$}
    0.58
     StatefulWidget
    0.54
    — 
    0.54
     enable
    0.52
     sayesinde
    0.52
     typedef
    0.52
    SpringRunner
    0.50
    Activations Density 0.546%

    No Known Activations