© 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. 18-GEMMASCOPE-RES-16K
    11. 883
    Prev
    Next
    INDEX
    Explanations

    phrases that describe effective communication and collaboration in a professional context

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

    Follows pronouns

    np_acts-logits-general · gemini-2.0-flash

    negotiation and initial agreements

    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
    richTextPanel
    -0.60
     AssemblyTitle
    -0.57
    出版年
    -0.57
    JvmStatic
    -0.56
     EconPapers
    -0.56
     ooit
    -0.56
     avenge
    -0.54
     JpaRepository
    -0.54
     σήμερα
    -0.54
    ToProps
    -0.54
    POSITIVE LOGITS
     agreed
    0.79
     initial
    0.78
    Negoti
    0.73
    全程
    0.71
     negotiation
    0.69
     during
    0.66
     upfront
    0.66
    initial
    0.65
    Initial
    0.65
     negotiating
    0.65
    Activations Density 0.225%

    No Known Activations