© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 17146
    Prev
    Next
    INDEX
    Explanations

    terms related to concessions and the act of conceding in negotiations or discussions

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

    concession or concede

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ry
    -0.47
    Ari
    -0.41
     Ara
    -0.38
    UPDATE
    -0.38
     Ari
    -0.38
     Wür
    -0.37
     FBI
    -0.37
     Ayuda
    -0.37
    Ry
    -0.36
     Brasília
    -0.36
    POSITIVE LOGITS
     Concession
    1.25
     concession
    1.12
     concessions
    1.03
     concede
    1.00
     conceding
    0.90
    cessions
    0.90
     conceded
    0.83
     concedes
    0.82
     CONC
    0.81
     concess
    0.76
    Activations Density 0.007%

    No Known Activations