© 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. 2-GEMMASCOPE-RES-16K
    6. 14591
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications and research terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.53
     strada
    -0.46
     Even
    -0.41
     παρά
    -0.40
    Even
    -0.40
    Downloaded
    -0.40
    campista
    -0.40
    omalainen
    -0.40
     personal
    -0.40
     sicher
    -0.40
    POSITIVE LOGITS
    ess
    0.88
    ss
    0.83
    iness
    0.80
    ESS
    0.78
    lessness
    0.74
    ISS
    0.72
    esss
    0.72
    SSSS
    0.72
    ness
    0.71
    esses
    0.71
    Activations Density 1.760%

    No Known Activations