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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5979
    Prev
    Next
    INDEX
    Explanations

    comments or explanations related to programming or technical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Māori
    -0.64
     să
    -0.64
    În
    -0.64
     Citroën
    -0.60
    portál
    -0.59
    código
    -0.59
     Hôtel
    -0.58
     Dacă
    -0.58
     cuánt
    -0.58
    ENCIÓN
    -0.58
    POSITIVE LOGITS
     proposito
    0.52
     Joao
    0.50
     moze
    0.49
     Suarez
    0.48
    calaure
    0.48
    unoz
    0.48
     megfe
    0.47
     Sao
    0.46
     Espan
    0.46
     Thats
    0.46
    Activations Density 0.244%

    No Known Activations