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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10740
    Prev
    Next
    INDEX
    Explanations

    business-related terminology and phrases associated with the film industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    People in entertainment and business

    np_acts-logits-general · gemini-2.0-flash

    agent or manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.59
    enfone
    -0.55
     redraw
    -0.54
    〗
    -0.53
     ostavi
    -0.52
     >::
    -0.52
    Билгалдахарш
    -0.52
     Manuals
    -0.49
    脚注の使い方
    -0.48
    omány
    -0.47
    POSITIVE LOGITS
     agent
    1.47
     agents
    1.33
    agent
    1.25
     Agent
    1.18
     agency
    1.15
     agente
    1.14
     AGENT
    1.14
    agents
    1.10
     Agents
    1.09
    Agent
    1.04
    Activations Density 0.194%

    No Known Activations