© 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. 15-GEMMASCOPE-RES-16K
    11. 12539
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of exploits or actions of characters, particularly focusing on narratives involving secret agents or espionage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.83
    enderror
    -0.66
     Италијани
    -0.64
     liné
    -0.62
     purpoſe
    -0.61
     InputDecoration
    -0.60
    ativement
    -0.59
     preſent
    -0.57
     Allociné
    -0.57
    AndEndTag
    -0.56
    POSITIVE LOGITS
     struggles
    0.64
     struggle
    0.59
     struggling
    0.57
     life
    0.55
     battling
    0.52
     explores
    0.51
     tale
    0.51
     struggled
    0.49
     travels
    0.49
    histoire
    0.49
    Activations Density 0.216%

    No Known Activations