© 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. 660
    Prev
    Next
    INDEX
    Explanations

    legal permissions and authorizations regarding intellectual property

    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
     trajets
    -0.52
    Anak
    -0.49
     Inquiries
    -0.48
    רְ
    -0.47
    bootstrapcdn
    -0.47
    Personendaten
    -0.45
    libft
    -0.45
     Triggers
    -0.45
    twimg
    -0.45
     noten
    -0.45
    POSITIVE LOGITS
     quæ
    0.86
     mijne
    0.75
     picioare
    0.69
    Rhestr
    0.67
     viață
    0.66
     statunit
    0.61
     giapp
    0.61
     þat
    0.61
     Romains
    0.60
     dreapta
    0.60
    Activations Density 2.679%

    No Known Activations