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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8044
    Prev
    Next
    INDEX
    Explanations

    references to websites and external links

    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
    fromCharCode
    -0.48
    fjspx
    -0.47
     propOrder
    -0.46
    исленность
    -0.42
    AnimationsModule
    -0.40
    发表于
    -0.37
    脚注の使い方
    -0.36
     gainera
    -0.36
     &___
    -0.36
     convaincre
    -0.36
    POSITIVE LOGITS
     website
    3.11
     websites
    2.47
     Website
    2.47
    website
    2.47
    Website
    2.34
     WEBSITE
    2.25
     webpage
    2.06
    WEBSITE
    2.05
    网站
    2.03
     site
    2.02
    Activations Density 0.519%

    No Known Activations