© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7461
    Prev
    Next
    INDEX
    Explanations

    references to legal roles and agency

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Legal and business agents

    np_acts-logits-general · gemini-2.0-flash

    agent or proxy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    setVerticalGroup
    -0.58
    Diweddarwch
    -0.56
    tagHelperRunner
    -0.53
     '\\;'
    -0.53
    期刊论文
    -0.53
    ThroughAttribute
    -0.51
     مشين
    -0.51
    hoeddwyd
    -0.50
    DebuggerNonUser
    -0.50
    ClCompile
    -0.50
    POSITIVE LOGITS
    代理
    0.97
     proxy
    0.96
     agent
    0.89
    proxy
    0.84
     Proxy
    0.81
     delegate
    0.79
     agents
    0.79
     proxies
    0.78
     delegated
    0.78
     代理
    0.77
    Activations Density 0.449%

    No Known Activations