© 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. 3761
    Prev
    Next
    INDEX
    Explanations

    elements related to biochemical processes and specific cellular components

    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
    ⓘ
    -0.54
    дев
    -0.52
    BufferedWriter
    -0.49
    enciaga
    -0.49
    kaper
    -0.49
     quiser
    -0.47
     saites
    -0.46
     capital
    -0.46
     Raton
    -0.45
    onghi
    -0.45
    POSITIVE LOGITS
    enumi
    1.01
     itſelf
    0.76
     مشين
    0.66
    enumii
    0.64
    脚注の使い方
    0.64
     Theſe
    0.63
     myſelf
    0.62
    Demografia
    0.61
    ſelves
    0.61
     purpoſe
    0.61
    Activations Density 2.013%

    No Known Activations