Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7843
    Prev
    Next
    INDEX
    Explanations

    references to programming or technical instructions related to applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.48
     يتيمه
    -0.48
     CreateTagHelper
    -0.45
     Kort
    -0.41
     anillos
    -0.41
     anillo
    -0.40
     sepol
    -0.40
    ngdoc
    -0.38
    lappe
    -0.37
     luces
    -0.37
    POSITIVE LOGITS
     bot
    0.79
    bot
    0.69
    Bot
    0.67
     Bot
    0.66
     Telegram
    0.66
     BOT
    0.65
     telegram
    0.60
     Bots
    0.59
    BOT
    0.57
     bots
    0.57
    Activations Density 0.114%

    No Known Activations