© 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. 1-GEMMASCOPE-RES-16K
    6. 15429
    Prev
    Next
    INDEX
    Explanations

    terms related to energy production and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.78
    RefNanny
    -0.57
    tvguidetime
    -0.56
    cdk
    -0.47
    IEVE
    -0.47
    aspectj
    -0.45
    στι
    -0.43
    ]^{-
    -0.43
    GIVEREF
    -0.42
    araman
    -0.42
    POSITIVE LOGITS
     препратки
    0.74
    StoryboardSegue
    0.68
     виправивши
    0.61
     oprot
    0.60
    verwijspagina
    0.59
     kaarangay
    0.58
     Signalez
    0.58
    Jeografia
    0.58
    ReusableCell
    0.57
     dAtA
    0.56
    Activations Density 1.339%

    No Known Activations